[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EPDYZH2HVEYY2V258DTFX4":3,"skill-same:01M7EPDYZH2HVEYY2V258DTFX4":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M7EPDYZH2HVEYY2V258DTFX4","mechanistic-interpretability-pyvene",null,"Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.","TanNhatCMS\u002Fjarvis","TanNhatCMS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113796420?v=4","01M753MV17KG5CD3152G3WQEQY","KietNT","01M7EKEDYVYQ6PWVJJMZ911VMX",0,"MIT","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-mechanistic-interpretability-pyvene\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mechanistic-interpretability-pyvene\ndescription: Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.\nversion: 1.0.0\nauthor: Orchestra Research\nlicense: MIT\ntags: [Causal Intervention, pyvene, Activation Patching, Causal Tracing, Interpretability]\ndependencies: [pyvene>=0.1.8, torch>=2.0.0, transformers>=4.30.0]\n---\n\n# pyvene: Causal Interventions for Neural Networks\n\npyvene is Stanford NLP's library for performing causal interventions on PyTorch models. It provides a declarative, dict-based framework for activation patching, causal tracing, and interchange intervention training - making intervention experiments reproducible and shareable.\n\n**GitHub**: [stanfordnlp\u002Fpyvene](https:\u002F\u002Fgithub.com\u002Fstanfordnlp\u002Fpyvene) (840+ stars)\n**Paper**: [pyvene: A Library for Understanding and Improving PyTorch Models via Interventions](https:\u002F\u002Faclanthology.org\u002F2024.naacl-demo.16) (NAACL 2024)\n\n## When to Use pyvene\n\n**Use pyvene when you need to:**\n- Perform causal tracing (ROME-style localization)\n- Run activation patching experiments\n- Conduct interchange intervention training (IIT)\n- Test causal hypotheses about model components\n- Share\u002Freproduce intervention experiments via HuggingFace\n- Work with any PyTorch architecture (not just transformers)\n\n**Consider alternatives when:**\n- You need exploratory activation analysis → Use **TransformerLens**\n- You want to train\u002Fanalyze SAEs → Use **SAELens**\n- You need remote execution on massive models → Use **nnsight**\n- You want lower-level control → Use **nnsight**\n\n## Installation\n\n```bash\npip install pyvene\n```\n\nStandard import:\n```python\nimport pyvene as pv\n```\n\n## Core Concepts\n\n### IntervenableModel\n\nThe main class that wraps any PyTorch model with intervention capabilities:\n\n```python\nimport pyvene as pv\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\n# Load base model\nmodel = AutoModelForCausalLM.from_pretrained(\"gpt2\")\ntokenizer = AutoTokenizer.from_pretrained(\"gpt2\")\n\n# Define intervention configuration\nconfig = pv.IntervenableConfig(\n    representations=[\n        pv.RepresentationConfig(\n            layer=8,\n            component=\"block_output\",\n            intervention_type=pv.VanillaIntervention,\n        )\n    ]\n)\n\n# Create intervenable model\nintervenable = pv.IntervenableModel(config, model)\n```\n\n### Intervention Types\n\n| Type | Description | Use Case |\n|------|-------------|----------|\n| `VanillaIntervention` | Swap activations between runs | Activation patching |\n| `AdditionIntervention` | Add activations to base run | Steering, ablation |\n| `SubtractionIntervention` | Subtract activations | Ablation |\n| `ZeroIntervention` | Zero out activations | Component knockout |\n| `RotatedSpaceIntervention` | DAS trainable intervention | Causal discovery |\n| `CollectIntervention` | Collect activations | Probing, analysis |\n\n### Component Targets\n\n```python\n# Available components to intervene on\ncomponents = [\n    \"block_input\",      # Input to transformer block\n    \"block_output\",     # Output of transformer block\n    \"mlp_input\",        # Input to MLP\n    \"mlp_output\",       # Output of MLP\n    \"mlp_activation\",   # MLP hidden activations\n    \"attention_input\",  # Input to attention\n    \"attention_output\", # Output of attention\n    \"attention_value_output\",  # Attention value vectors\n    \"query_output\",     # Query vectors\n    \"key_output\",       # Key vectors\n    \"value_output\",     # Value vectors\n    \"head_attention_value_output\",  # Per-head values\n]\n```\n\n## Workflow 1: Causal Tracing (ROME-style)\n\nLocate where factual associations are stored by corrupting inputs and restoring activations.\n\n### Step-by-Step\n\n```python\nimport pyvene as pv\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\nimport torch\n\nmodel = AutoModelForCausalLM.from_pretrained(\"gpt2-xl\")\ntokenizer = AutoTokenizer.from_pretrained(\"gpt2-xl\")\n\n# 1. Define clean and corrupted inputs\nclean_prompt = \"The Space Needle is in downtown\"\ncorrupted_prompt = \"The ##### ###### ## ## ########\"  # Noise\n\nclean_tokens = tokenizer(clean_prompt, return_tensors=\"pt\")\ncorrupted_tokens = tokenizer(corrupted_prompt, return_tensors=\"pt\")\n\n# 2. Get clean activations (source)\nwith torch.no_grad():\n    clean_outputs = model(**clean_tokens, output_hidden_states=True)\n    clean_states = clean_outputs.hidden_states\n\n# 3. Define restoration intervention\ndef run_causal_trace(layer, position):\n    \"\"\"Restore clean activation at specific layer and position.\"\"\"\n    config = pv.IntervenableConfig(\n        representations=[\n            pv.RepresentationConfig(\n                layer=layer,\n                component=\"block_output\",\n                intervention_type=pv.VanillaIntervention,\n                unit=\"pos\",\n                max_number_of_units=1,\n            )\n        ]\n    )\n\n    intervenable = pv.IntervenableModel(config, model)\n\n    # Run with intervention\n    _, patched_outputs = intervenable(\n        base=corrupted_tokens,\n        sources=[clean_tokens],\n        unit_locations={\"sources->base\": ([[[position]]], [[[position]]])},\n        output_original_output=True,\n    )\n\n    # Return probability of correct token\n    probs = torch.softmax(patched_outputs.logits[0, -1], dim=-1)\n    seattle_token = tokenizer.encode(\" Seattle\")[0]\n    return probs[seattle_token].item()\n\n# 4. Sweep over layers and positions\nn_layers = model.config.n_layer\nseq_len = clean_tokens[\"input_ids\"].shape[1]\n\nresults = torch.zeros(n_layers, seq_len)\nfor layer in range(n_layers):\n    for pos in range(seq_len):\n        results[layer, pos] = run_causal_trace(layer, pos)\n\n# 5. Visualize (layer x position heatmap)\n# High values indicate causal importance\n```\n\n### Checklist\n- [ ] Prepare clean prompt with target factual association\n- [ ] Create corrupted version (noise or counterfactual)\n- [ ] Define intervention config for each (layer, position)\n- [ ] Run patching sweep\n- [ ] Identify causal hotspots in heatmap\n\n## Workflow 2: Activation Patching for Circuit Analysis\n\nTest which components are necessary for a specific behavior.\n\n### Step-by-Step\n\n```python\nimport pyvene as pv\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\nimport torch\n\nmodel = AutoModelForCausalLM.from_pretrained(\"gpt2\")\ntokenizer = AutoTokenizer.from_pretrained(\"gpt2\")\n\n# IOI task setup\nclean_prompt = \"When John and Mary went to the store, Mary gave a bottle to\"\ncorrupted_prompt = \"When John and Mary went to the store, John gave a bottle to\"\n\nclean_tokens = tokenizer(clean_prompt, return_tensors=\"pt\")\ncorrupted_tokens = tokenizer(corrupted_prompt, return_tensors=\"pt\")\n\njohn_token = tokenizer.encode(\" John\")[0]\nmary_token = tokenizer.encode(\" Mary\")[0]\n\ndef logit_diff(logits):\n    \"\"\"IO - S logit difference.\"\"\"\n    return logits[0, -1, john_token] - logits[0, -1, mary_token]\n\n# Patch attention output at each layer\ndef patch_attention(layer):\n    config = pv.IntervenableConfig(\n        representations=[\n            pv.RepresentationConfig(\n                layer=layer,\n                component=\"attention_output\",\n                intervention_type=pv.VanillaIntervention,\n            )\n        ]\n    )\n\n    intervenable = pv.IntervenableModel(config, model)\n\n    _, patched_outputs = intervenable(\n        base=corrupted_tokens,\n        sources=[clean_tokens],\n    )\n\n    return logit_diff(patched_outputs.logits).item()\n\n# Find which layers matter\nresults = []\nfor layer in range(model.config.n_layer):\n    diff = patch_attention(layer)\n    results.append(diff)\n    print(f\"Layer {layer}: logit diff = {diff:.3f}\")\n```\n\n## Workflow 3: Interchange Intervention Training (IIT)\n\nTrain interventions to discover causal structure.\n\n### Step-by-Step\n\n```python\nimport pyvene as pv\nfrom transformers import AutoModelForCausalLM\nimport torch\n\nmodel = AutoModelForCausalLM.from_pretrained(\"gpt2\")\n\n# 1. Define trainable intervention\nconfig = pv.IntervenableConfig(\n    representations=[\n        pv.RepresentationConfig(\n            layer=6,\n            component=\"block_output\",\n            intervention_type=pv.RotatedSpaceIntervention,  # Trainable\n            low_rank_dimension=64,  # Learn 64-dim subspace\n        )\n    ]\n)\n\nintervenable = pv.IntervenableModel(config, model)\n\n# 2. Set up training\noptimizer = torch.optim.Adam(\n    intervenable.get_trainable_parameters(),\n    lr=1e-4\n)\n\n# 3. Training loop (simplified)\nfor base_input, source_input, target_output in dataloader:\n    optimizer.zero_grad()\n\n    _, outputs = intervenable(\n        base=base_input,\n        sources=[source_input],\n    )\n\n    loss = criterion(outputs.logits, target_output)\n    loss.backward()\n    optimizer.step()\n\n# 4. Analyze learned intervention\n# The rotation matrix reveals causal subspace\nrotation = intervenable.interventions[\"layer.6.block_output\"][0].rotate_layer\n```\n\n### DAS (Distributed Alignment Search)\n\n```python\n# Low-rank rotation finds interpretable subspaces\nconfig = pv.IntervenableConfig(\n    representations=[\n        pv.RepresentationConfig(\n            layer=8,\n            component=\"block_output\",\n            intervention_type=pv.LowRankRotatedSpaceIntervention,\n            low_rank_dimension=1,  # Find 1D causal direction\n        )\n    ]\n)\n```\n\n## Workflow 4: Model Steering (Honest LLaMA)\n\nSteer model behavior during generation.\n\n```python\nimport pyvene as pv\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\nmodel = AutoModelForCausalLM.from_pretrained(\"meta-llama\u002FLlama-2-7b-hf\")\ntokenizer = AutoTokenizer.from_pretrained(\"meta-llama\u002FLlama-2-7b-hf\")\n\n# Load pre-trained steering intervention\nintervenable = pv.IntervenableModel.load(\n    \"zhengxuanzenwu\u002Fintervenable_honest_llama2_chat_7B\",\n    model=model,\n)\n\n# Generate with steering\nprompt = \"Is the earth flat?\"\ninputs = tokenizer(prompt, return_tensors=\"pt\")\n\n# Intervention applied during generation\noutputs = intervenable.generate(\n    inputs,\n    max_new_tokens=100,\n    do_sample=False,\n)\n\nprint(tokenizer.decode(outputs[0]))\n```\n\n## Saving and Sharing Interventions\n\n```python\n# Save locally\nintervenable.save(\".\u002Fmy_intervention\")\n\n# Load from local\nintervenable = pv.IntervenableModel.load(\n    \".\u002Fmy_intervention\",\n    model=model,\n)\n\n# Share on HuggingFace\nintervenable.save_intervention(\"username\u002Fmy-intervention\")\n\n# Load from HuggingFace\nintervenable = pv.IntervenableModel.load(\n    \"username\u002Fmy-intervention\",\n    model=model,\n)\n```\n\n## Common Issues & Solutions\n\n### Issue: Wrong intervention location\n```python\n# WRONG: Incorrect component name\nconfig = pv.RepresentationConfig(\n    component=\"mlp\",  # Not valid!\n)\n\n# RIGHT: Use exact component name\nconfig = pv.RepresentationConfig(\n    component=\"mlp_output\",  # Valid\n)\n```\n\n### Issue: Dimension mismatch\n```python\n# Ensure source and base have compatible shapes\n# For position-specific interventions:\nconfig = pv.RepresentationConfig(\n    unit=\"pos\",\n    max_number_of_units=1,  # Intervene on single position\n)\n\n# Specify locations explicitly\nintervenable(\n    base=base_tokens,\n    sources=[source_tokens],\n    unit_locations={\"sources->base\": ([[[5]]], [[[5]]])},  # Position 5\n)\n```\n\n### Issue: Memory with large models\n```python\n# Use gradient checkpointing\nmodel.gradient_checkpointing_enable()\n\n# Or intervene on fewer components\nconfig = pv.IntervenableConfig(\n    representations=[\n        pv.RepresentationConfig(\n            layer=8,  # Single layer instead of all\n            component=\"block_output\",\n        )\n    ]\n)\n```\n\n### Issue: LoRA integration\n```python\n# pyvene v0.1.8+ supports LoRAs as interventions\nconfig = pv.RepresentationConfig(\n    intervention_type=pv.LoRAIntervention,\n    low_rank_dimension=16,\n)\n```\n\n## Key Classes Reference\n\n| Class | Purpose |\n|-------|---------|\n| `IntervenableModel` | Main wrapper for interventions |\n| `IntervenableConfig` | Configuration container |\n| `RepresentationConfig` | Single intervention specification |\n| `VanillaIntervention` | Activation swapping |\n| `RotatedSpaceIntervention` | Trainable DAS intervention |\n| `CollectIntervention` | Activation collection |\n\n## Supported Models\n\npyvene works with any PyTorch model. Tested on:\n- GPT-2 (all sizes)\n- LLaMA \u002F LLaMA-2\n- Pythia\n- Mistral \u002F Mixtral\n- OPT\n- BLIP (vision-language)\n- ESM (protein models)\n- Mamba (state space)\n\n## Reference Documentation\n\nFor detailed API documentation, tutorials, and advanced usage, see the `references\u002F` folder:\n\n| File | Contents |\n|------|----------|\n| [references\u002FREADME.md](references\u002FREADME.md) | Overview and quick start guide |\n| [references\u002Fapi.md](references\u002Fapi.md) | Complete API reference for IntervenableModel, intervention types, configurations |\n| [references\u002Ftutorials.md](references\u002Ftutorials.md) | Step-by-step tutorials for causal tracing, activation patching, DAS |\n\n## External Resources\n\n### Tutorials\n- [pyvene 101](https:\u002F\u002Fstanfordnlp.github.io\u002Fpyvene\u002Ftutorials\u002Fpyvene_101.html)\n- [Causal Tracing Tutorial](https:\u002F\u002Fstanfordnlp.github.io\u002Fpyvene\u002Ftutorials\u002Fadvanced_tutorials\u002FCausal_Tracing.html)\n- [IOI Circuit Replication](https:\u002F\u002Fstanfordnlp.github.io\u002Fpyvene\u002Ftutorials\u002Fadvanced_tutorials\u002FIOI_Replication.html)\n- [DAS Introduction](https:\u002F\u002Fstanfordnlp.github.io\u002Fpyvene\u002Ftutorials\u002Fadvanced_tutorials\u002FDAS_Main_Introduction.html)\n\n### Papers\n- [Locating and Editing Factual Associations in GPT](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.05262) - Meng et al. (2022)\n- [Inference-Time Intervention](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.03341) - Li et al. (2023)\n- [Interpretability in the Wild](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.00593) - Wang et al. (2022)\n\n### Official Documentation\n- [Official Docs](https:\u002F\u002Fstanfordnlp.github.io\u002Fpyvene\u002F)\n- [API Reference](https:\u002F\u002Fstanfordnlp.github.io\u002Fpyvene\u002Fapi\u002F)\n\n## Comparison with Other Tools\n\n| Feature | pyvene | TransformerLens | nnsight |\n|---------|--------|-----------------|---------|\n| Declarative config | Yes | No | No |\n| HuggingFace sharing | Yes | No | No |\n| Trainable interventions | Yes | Limited | Yes |\n| Any PyTorch model | Yes | Transformers only | Yes |\n| Remote execution | No | No | Yes (NDIF) |\n","# pyvene: Causal Interventions for Neural Networks\n\npyvene is Stanford NLP's library for performing causal interventions on PyTorch models. It provides a declarative, dict-based framework for activation patching, causal tracing, and interchange intervention training - making intervention experiments reproducible and shareable.\n\n**GitHub**: [stanfordnlp\u002Fpyvene](https:\u002F\u002Fgithub.com\u002Fstanfordnlp\u002Fpyvene) (840+ stars)\n**Paper**: [pyvene: A Library for Understanding and Improving PyTorch Models via Interventions](https:\u002F\u002Faclanthology.org\u002F2024.naacl-demo.16) (NAACL 2024)\n\n## When to Use pyvene\n\n**Use pyvene when you need to:**\n- Perform causal tracing (ROME-style localization)\n- Run activation patching experiments\n- Conduct interchange intervention training (IIT)\n- Test causal hypotheses about model components\n- Share\u002Freproduce intervention experiments via HuggingFace\n- Work with any PyTorch architecture (not just transformers)\n\n**Consider alternatives when:**\n- You need exploratory activation analysis → Use **TransformerLens**\n- You want to train\u002Fanalyze SAEs → Use **SAELens**\n- You need remote execution on massive models → Use **nnsight**\n- You want lower-level control → Use **nnsight**\n\n## Installation\n\n```bash\npip install pyvene\n```\n\nStandard import:\n```python\nimport pyvene as pv\n```\n\n## Core Concepts\n\n### IntervenableModel\n\nThe main class that wraps any PyTorch model with intervention capabilities:\n\n```python\nimport pyvene as pv\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\n# Load base model\nmodel = AutoModelForCausalLM.from_pretrained(\"gpt2\")\ntokenizer = AutoTokenizer.from_pretrained(\"gpt2\")\n\n# Define intervention configuration\nconfig = pv.IntervenableConfig(\n    representations=[\n        pv.RepresentationConfig(\n            layer=8,\n            component=\"block_output\",\n            intervention_type=pv.VanillaIntervention,\n        )\n    ]\n)\n\n# Create intervenable model\nintervenable = pv.IntervenableModel(config, model)\n```\n\n### Intervention Types\n\n| Type | Description | Use Case |\n|------|-------------|----------|\n| `VanillaIntervention` | Swap activations between runs | Activation patching |\n| `AdditionIntervention` | Add activations to base run | Steering, ablation |\n| `SubtractionIntervention` | Subtract activations | Ablation |\n| `ZeroIntervention` | Zero out activations | Component knockout |\n| `RotatedSpaceIntervention` | DAS trainable intervention | Causal discovery |\n| `CollectIntervention` | Collect activations | Probing, analysis |\n\n### Component Targets\n\n```python\n# Available components to intervene on\ncomponents = [\n    \"block_input\",      # Input to transformer block\n    \"block_output\",     # Output of transformer block\n    \"mlp_input\",        # Input to MLP\n    \"mlp_output\",       # Output of MLP\n    \"mlp_activation\",   # MLP hidden activations\n    \"attention_input\",  # Input to attention\n    \"attention_output\", # Output of attention\n    \"attention_value_output\",  # Attention value vectors\n    \"query_output\",     # Query vectors\n    \"key_output\",       # Key vectors\n    \"value_output\",     # Value vectors\n    \"head_attention_value_output\",  # Per-head values\n]\n```\n\n## Workflow 1: Causal Tracing (ROME-style)\n\nLocate where factual associations are stored by corrupting inputs and restoring activations.\n\n### Step-by-Step\n\n```python\nimport pyvene as pv\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\nimport torch\n\nmodel = AutoModelForCausalLM.from_pretrained(\"gpt2-xl\")\ntokenizer = AutoTokenizer.from_pretrained(\"gpt2-xl\")\n\n# 1. Define clean and corrupted inputs\nclean_prompt = \"The Space Needle is in downtown\"\ncorrupted_prompt = \"The ##### ###### ## ## ########\"  # Noise\n\nclean_tokens = tokenizer(clean_prompt, return_tensors=\"pt\")\ncorrupted_tokens = tokenizer(corrupted_prompt, return_tensors=\"pt\")\n\n# 2. Get clean activations (source)\nwith torch.no_grad():\n    clean_outputs = model(**clean_tokens, output_hidden_states=True)\n    clean_states = clean_outputs.hidden_states\n\n# 3. Define restoration intervention\ndef run_causal_trace(layer, position):\n    \"\"\"Restore clean activation at specific layer and position.\"\"\"\n    config = pv.IntervenableConfig(\n        representations=[\n            pv.RepresentationConfig(\n                layer=layer,\n                component=\"block_output\",\n                intervention_type=pv.VanillaIntervention,\n                unit=\"pos\",\n                max_number_of_units=1,\n            )\n        ]\n    )\n\n    intervenable = pv.IntervenableModel(config, model)\n\n    # Run with intervention\n    _, patched_outputs = intervenable(\n        base=corrupted_tokens,\n        sources=[clean_tokens],\n        unit_locations={\"sources->base\": ([[[position]]], [[[position]]])},\n        output_original_output=True,\n    )\n\n    # Return probability of correct token\n    probs = torch.softmax(patched_outputs.logits[0, -1], dim=-1)\n    seattle_token = tokenizer.encode(\" Seattle\")[0]\n    return probs[seattle_token].item()\n\n# 4. Sweep over layers and positions\nn_layers = model.config.n_layer\nseq_len = clean_tokens[\"input_ids\"].shape[1]\n\nresults = torch.zeros(n_layers, seq_len)\nfor layer in range(n_layers):\n    for pos in range(seq_len):\n        results[layer, pos] = run_causal_trace(layer, pos)\n\n# 5. Visualize (layer x position heatmap)\n# High values indicate causal importance\n```\n\n### Checklist\n- [ ] Prepare clean prompt with target factual association\n- [ ] Create corrupted version (noise or counterfactual)\n- [ ] Define intervention config for each (layer, position)\n- [ ] Run patching sweep\n- [ ] Identify causal hotspots in heatmap\n\n## Workflow 2: Activation Patching for Circuit Analysis\n\nTest which components are necessary for a specific behavior.\n\n### Step-by-Step\n\n```python\nimport pyvene as pv\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\nimport torch\n\nmodel = AutoModelForCausalLM.from_pretrained(\"gpt2\")\ntokenizer = AutoTokenizer.from_pretrained(\"gpt2\")\n\n# IOI task setup\nclean_prompt = \"When John and Mary went to the store, Mary gave a bottle to\"\ncorrupted_prompt = \"When John and Mary went to the store, John gave a bottle to\"\n\nclean_tokens = tokenizer(clean_prompt, return_tensors=\"pt\")\ncorrupted_tokens = tokenizer(corrupted_prompt, return_tensors=\"pt\")\n\njohn_token = tokenizer.encode(\" John\")[0]\nmary_token = tokenizer.encode(\" Mary\")[0]\n\ndef logit_diff(logits):\n    \"\"\"IO - S logit difference.\"\"\"\n    return logits[0, -1, john_token] - logits[0, -1, mary_token]\n\n# Patch attention output at each layer\ndef patch_attention(layer):\n    config = pv.IntervenableConfig(\n        representations=[\n            pv.RepresentationConfig(\n                layer=layer,\n                component=\"attention_output\",\n                intervention_type=pv.VanillaIntervention,\n            )\n        ]\n    )\n\n    intervenable = pv.IntervenableModel(config, model)\n\n    _, patched_outputs = intervenable(\n        base=corrupted_tokens,\n        sources=[clean_tokens],\n    )\n\n    return logit_diff(patched_outputs.logits).item()\n\n# Find which layers matter\nresults = []\nfor layer in range(model.config.n_layer):\n    diff = patch_attention(layer)\n    results.append(diff)\n    print(f\"Layer {layer}: logit diff = {diff:.3f}\")\n```\n\n## Workflow 3: Interchange Intervention Training (IIT)\n\nTrain interventions to discover causal structure.\n\n### Step-by-Step\n\n```python\nimport pyvene as pv\nfrom transformers import AutoModelForCausalLM\nimport torch\n\nmodel = AutoModelForCausalLM.from_pretrained(\"gpt2\")\n\n# 1. Define trainable intervention\nconfig = pv.IntervenableConfig(\n    representations=[\n        pv.RepresentationConfig(\n            layer=6,\n            component=\"block_output\",\n            intervention_type=pv.RotatedSpaceIntervention,  # Trainable\n            low_rank_dimension=64,  # Learn 64-dim subspace\n        )\n    ]\n)\n\nintervenable = pv.IntervenableModel(config, model)\n\n# 2. Set up training\noptimizer = torch.optim.Adam(\n    intervenable.get_trainable_parameters(),\n    lr=1e-4\n)\n\n# 3. Training loop (simplified)\nfor base_input, source_input, target_output in dataloader:\n    optimizer.zero_grad()\n\n    _, outputs = intervenable(\n        base=base_input,\n        sources=[source_input],\n    )\n\n    loss = criterion(outputs.logits, target_output)\n    loss.backward()\n    optimizer.step()\n\n# 4. Analyze learned intervention\n# The rotation matrix reveals causal subspace\nrotation = intervenable.interventions[\"layer.6.block_output\"][0].rotate_layer\n```\n\n### DAS (Distributed Alignment Search)\n\n```python\n# Low-rank rotation finds interpretable subspaces\nconfig = pv.IntervenableConfig(\n    representations=[\n        pv.RepresentationConfig(\n            layer=8,\n            component=\"block_output\",\n            intervention_type=pv.LowRankRotatedSpaceIntervention,\n            low_rank_dimension=1,  # Find 1D causal direction\n        )\n    ]\n)\n```\n\n## Workflow 4: Model Steering (Honest LLaMA)\n\nSteer model behavior during generation.\n\n```python\nimport pyvene as pv\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\nmodel = AutoModelForCausalLM.from_pretrained(\"meta-llama\u002FLlama-2-7b-hf\")\ntokenizer = AutoTokenizer.from_pretrained(\"meta-llama\u002FLlama-2-7b-hf\")\n\n# Load pre-trained steering intervention\nintervenable = pv.IntervenableModel.load(\n    \"zhengxuanzenwu\u002Fintervenable_honest_llama2_chat_7B\",\n    model=model,\n)\n\n# Generate with steering\nprompt = \"Is the earth flat?\"\ninputs = tokenizer(prompt, return_tensors=\"pt\")\n\n# Intervention applied during generation\noutputs = intervenable.generate(\n    inputs,\n    max_new_tokens=100,\n    do_sample=False,\n)\n\nprint(tokenizer.decode(outputs[0]))\n```\n\n## Saving and Sharing Interventions\n\n```python\n# Save locally\nintervenable.save(\".\u002Fmy_intervention\")\n\n# Load from local\nintervenable = pv.IntervenableModel.load(\n    \".\u002Fmy_intervention\",\n    model=model,\n)\n\n# Share on HuggingFace\nintervenable.save_intervention(\"username\u002Fmy-intervention\")\n\n# Load from HuggingFace\nintervenable = pv.IntervenableModel.load(\n    \"username\u002Fmy-intervention\",\n    model=model,\n)\n```\n\n## Common Issues & Solutions\n\n### Issue: Wrong intervention location\n```python\n# WRONG: Incorrect component name\nconfig = pv.RepresentationConfig(\n    component=\"mlp\",  # Not valid!\n)\n\n# RIGHT: Use exact component name\nconfig = pv.RepresentationConfig(\n    component=\"mlp_output\",  # Valid\n)\n```\n\n### Issue: Dimension mismatch\n```python\n# Ensure source and base have compatible shapes\n# For position-specific interventions:\nconfig = pv.RepresentationConfig(\n    unit=\"pos\",\n    max_number_of_units=1,  # Intervene on single position\n)\n\n# Specify locations explicitly\nintervenable(\n    base=base_tokens,\n    sources=[source_tokens],\n    unit_locations={\"sources->base\": ([[[5]]], [[[5]]])},  # Position 5\n)\n```\n\n### Issue: Memory with large models\n```python\n# Use gradient checkpointing\nmodel.gradient_checkpointing_enable()\n\n# Or intervene on fewer components\nconfig = pv.IntervenableConfig(\n    representations=[\n        pv.RepresentationConfig(\n            layer=8,  # Single layer instead of all\n            component=\"block_output\",\n        )\n    ]\n)\n```\n\n### Issue: LoRA integration\n```python\n# pyvene v0.1.8+ supports LoRAs as interventions\nconfig = pv.RepresentationConfig(\n    intervention_type=pv.LoRAIntervention,\n    low_rank_dimension=16,\n)\n```\n\n## Key Classes Reference\n\n| Class | Purpose |\n|-------|---------|\n| `IntervenableModel` | Main wrapper for interventions |\n| `IntervenableConfig` | Configuration container |\n| `RepresentationConfig` | Single intervention specification |\n| `VanillaIntervention` | Activation swapping |\n| `RotatedSpaceIntervention` | Trainable DAS intervention |\n| `CollectIntervention` | Activation collection |\n\n## Supported Models\n\npyvene works with any PyTorch model. Tested on:\n- GPT-2 (all sizes)\n- LLaMA \u002F LLaMA-2\n- Pythia\n- Mistral \u002F Mixtral\n- OPT\n- BLIP (vision-language)\n- ESM (protein models)\n- Mamba (state space)\n\n## Reference Documentation\n\nFor detailed API documentation, tutorials, and advanced usage, see the `references\u002F` folder:\n\n| File | Contents |\n|------|----------|\n| [references\u002FREADME.md](references\u002FREADME.md) | Overview and quick start guide |\n| [references\u002Fapi.md](references\u002Fapi.md) | Complete API reference for IntervenableModel, intervention types, configurations |\n| [references\u002Ftutorials.md](references\u002Ftutorials.md) | Step-by-step tutorials for causal tracing, activation patching, DAS |\n\n## External Resources\n\n### Tutorials\n- [pyvene 101](https:\u002F\u002Fstanfordnlp.github.io\u002Fpyvene\u002Ftutorials\u002Fpyvene_101.html)\n- [Causal Tracing Tutorial](https:\u002F\u002Fstanfordnlp.github.io\u002Fpyvene\u002Ftutorials\u002Fadvanced_tutorials\u002FCausal_Tracing.html)\n- [IOI Circuit Replication](https:\u002F\u002Fstanfordnlp.github.io\u002Fpyvene\u002Ftutorials\u002Fadvanced_tutorials\u002FIOI_Replication.html)\n- [DAS Introduction](https:\u002F\u002Fstanfordnlp.github.io\u002Fpyvene\u002Ftutorials\u002Fadvanced_tutorials\u002FDAS_Main_Introduction.html)\n\n### Papers\n- [Locating and Editing Factual Associations in GPT](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.05262) - Meng et al. (2022)\n- [Inference-Time Intervention](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.03341) - Li et al. (2023)\n- [Interpretability in the Wild](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.00593) - Wang et al. (2022)\n\n### Official Documentation\n- [Official Docs](https:\u002F\u002Fstanfordnlp.github.io\u002Fpyvene\u002F)\n- [API Reference](https:\u002F\u002Fstanfordnlp.github.io\u002Fpyvene\u002Fapi\u002F)\n\n## Comparison with Other Tools\n\n| Feature | pyvene | TransformerLens | nnsight |\n|---------|--------|-----------------|---------|\n| Declarative config | Yes | No | No |\n| HuggingFace sharing | Yes | No | No |\n| Trainable interventions | Yes | Limited | Yes |\n| Any PyTorch model | Yes | Transformers only | Yes |\n| Remote execution | No | No | Yes (NDIF) |\n",{"name":5,"tags":24,"author":30,"license":15,"version":31,"description":7,"dependencies":32},[25,26,27,28,29],"Causal Intervention","pyvene","Activation Patching","Causal Tracing","Interpretability","Orchestra Research","1.0.0",[33,34,35],"pyvene>=0.1.8","torch>=2.0.0","transformers>=4.30.0","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-imp-mechanistic-interpretability-pyvene",1,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis","https:\u002F\u002Fgithub.com\u002FTanNhatCMS","https:\u002F\u002Fmrkiet.name.vn","2026-11-07 14:23:08",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add TanNhatCMS\u002Fjarvis --skill mechanistic-interpretability-pyvene",{"tool":50,"command":51},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill mechanistic-interpretability-pyvene",{"tool":53,"command":54},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill mechanistic-interpretability-pyvene","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-mechanistic-interpretability-pyvene\u002FSKILL.md",true,[58,64,68],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fapi.md","REFERENCE","参考文档",7871,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-mechanistic-interpretability-pyvene\u002Freferences\u002Fapi.md",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002FREADME.md",2105,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-mechanistic-interpretability-pyvene\u002Freferences\u002FREADME.md",{"path":69,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Ftutorials.md",10111,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-mechanistic-interpretability-pyvene\u002Freferences\u002Ftutorials.md",[73,80,88,95,102,109],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7EWYJR0J8DARY7E59Z6Y9MV","web-scrape","Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open\u002Ffetch fails on JS-heavy pages, or when you need clean markdown\u002Fstructured extraction from a site. Requires FIRECRAWL_API_KEY.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fweb-scrape\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7EWYBN5P6F2AJG3FR24T9BP","design-taste-frontend","tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML\u002FCSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, \"AI-made\", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7EWY8FQFNQ2GB7NZZWGSSDX","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-tdd\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7EWY5SHBFRH1HDHVWM9K7TV","systematic-debugging","Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-debugging\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7EWY3NM0Z0JAKS7HDZ24K66","requesting-code-review","Use when completing tasks, implementing major features, or before merging to verify work meets requirements","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-code-review\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7EWY0WRMWX4M9ZFY0WKC593","brainstorming","You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-brainstorming\u002FSKILL.md",[],[]]