[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FCD0F6E6QRFS944PFVQZTG":3,"skill-same:01M7FCD0F6E6QRFS944PFVQZTG":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":6,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M7FCD0F6E6QRFS944PFVQZTG","sparse-autoencoder-training",null,"Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.","CZX-LBJ\u002Fdeepseek-science","CZX-LBJ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204594689?v=4","01M7FC59WQ9PFXT04MKGJDCFFT","czx","01M7FC59XB2GW0BKWN9JTDBQS7",1,"MIT","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fai-research-skills\u002F04-mechanistic-interpretability\u002Fsaelens\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: sparse-autoencoder-training\ndescription: Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.\nversion: 1.0.0\nauthor: Orchestra Research\nlicense: MIT\ntags: [Sparse Autoencoders, SAE, Mechanistic Interpretability, Feature Discovery, Superposition]\ndependencies: [sae-lens>=6.0.0, transformer-lens>=2.0.0, torch>=2.0.0]\n---\n\n# SAELens: Sparse Autoencoders for Mechanistic Interpretability\n\nSAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing polysemantic neural network activations into sparse, interpretable features. Based on Anthropic's groundbreaking research on monosemanticity.\n\n**GitHub**: [jbloomAus\u002FSAELens](https:\u002F\u002Fgithub.com\u002FjbloomAus\u002FSAELens) (1,100+ stars)\n\n## The Problem: Polysemanticity & Superposition\n\nIndividual neurons in neural networks are **polysemantic** - they activate in multiple, semantically distinct contexts. This happens because models use **superposition** to represent more features than they have neurons, making interpretability difficult.\n\n**SAEs solve this** by decomposing dense activations into sparse, monosemantic features - typically only a small number of features activate for any given input, and each feature corresponds to an interpretable concept.\n\n## When to Use SAELens\n\n**Use SAELens when you need to:**\n- Discover interpretable features in model activations\n- Understand what concepts a model has learned\n- Study superposition and feature geometry\n- Perform feature-based steering or ablation\n- Analyze safety-relevant features (deception, bias, harmful content)\n\n**Consider alternatives when:**\n- You need basic activation analysis → Use **TransformerLens** directly\n- You want causal intervention experiments → Use **pyvene** or **TransformerLens**\n- You need production steering → Consider direct activation engineering\n\n## Installation\n\n```bash\npip install sae-lens\n```\n\nRequirements: Python 3.10+, transformer-lens>=2.0.0\n\n## Core Concepts\n\n### What SAEs Learn\n\nSAEs are trained to reconstruct model activations through a sparse bottleneck:\n\n```\nInput Activation → Encoder → Sparse Features → Decoder → Reconstructed Activation\n    (d_model)       ↓        (d_sae >> d_model)    ↓         (d_model)\n                 sparsity                      reconstruction\n                 penalty                          loss\n```\n\n**Loss Function**: `MSE(original, reconstructed) + L1_coefficient × L1(features)`\n\n### Key Validation (Anthropic Research)\n\nIn \"Towards Monosemanticity\", human evaluators found **70% of SAE features genuinely interpretable**. Features discovered include:\n- DNA sequences, legal language, HTTP requests\n- Hebrew text, nutrition statements, code syntax\n- Sentiment, named entities, grammatical structures\n\n## Workflow 1: Loading and Analyzing Pre-trained SAEs\n\n### Step-by-Step\n\n```python\nfrom transformer_lens import HookedTransformer\nfrom sae_lens import SAE\n\n# 1. Load model and pre-trained SAE\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\", device=\"cuda\")\nsae, cfg_dict, sparsity = SAE.from_pretrained(\n    release=\"gpt2-small-res-jb\",\n    sae_id=\"blocks.8.hook_resid_pre\",\n    device=\"cuda\"\n)\n\n# 2. Get model activations\ntokens = model.to_tokens(\"The capital of France is Paris\")\n_, cache = model.run_with_cache(tokens)\nactivations = cache[\"resid_pre\", 8]  # [batch, pos, d_model]\n\n# 3. Encode to SAE features\nsae_features = sae.encode(activations)  # [batch, pos, d_sae]\nprint(f\"Active features: {(sae_features > 0).sum()}\")\n\n# 4. Find top features for each position\nfor pos in range(tokens.shape[1]):\n    top_features = sae_features[0, pos].topk(5)\n    token = model.to_str_tokens(tokens[0, pos:pos+1])[0]\n    print(f\"Token '{token}': features {top_features.indices.tolist()}\")\n\n# 5. Reconstruct activations\nreconstructed = sae.decode(sae_features)\nreconstruction_error = (activations - reconstructed).norm()\n```\n\n### Available Pre-trained SAEs\n\n| Release | Model | Layers |\n|---------|-------|--------|\n| `gpt2-small-res-jb` | GPT-2 Small | Multiple residual streams |\n| `gemma-2b-res` | Gemma 2B | Residual streams |\n| Various on HuggingFace | Search tag `saelens` | Various |\n\n### Checklist\n- [ ] Load model with TransformerLens\n- [ ] Load matching SAE for target layer\n- [ ] Encode activations to sparse features\n- [ ] Identify top-activating features per token\n- [ ] Validate reconstruction quality\n\n## Workflow 2: Training a Custom SAE\n\n### Step-by-Step\n\n```python\nfrom sae_lens import SAE, LanguageModelSAERunnerConfig, SAETrainingRunner\n\n# 1. Configure training\ncfg = LanguageModelSAERunnerConfig(\n    # Model\n    model_name=\"gpt2-small\",\n    hook_name=\"blocks.8.hook_resid_pre\",\n    hook_layer=8,\n    d_in=768,  # Model dimension\n\n    # SAE architecture\n    architecture=\"standard\",  # or \"gated\", \"topk\"\n    d_sae=768 * 8,  # Expansion factor of 8\n    activation_fn=\"relu\",\n\n    # Training\n    lr=4e-4,\n    l1_coefficient=8e-5,  # Sparsity penalty\n    l1_warm_up_steps=1000,\n    train_batch_size_tokens=4096,\n    training_tokens=100_000_000,\n\n    # Data\n    dataset_path=\"monology\u002Fpile-uncopyrighted\",\n    context_size=128,\n\n    # Logging\n    log_to_wandb=True,\n    wandb_project=\"sae-training\",\n\n    # Checkpointing\n    checkpoint_path=\"checkpoints\",\n    n_checkpoints=5,\n)\n\n# 2. Train\ntrainer = SAETrainingRunner(cfg)\nsae = trainer.run()\n\n# 3. Evaluate\nprint(f\"L0 (avg active features): {trainer.metrics['l0']}\")\nprint(f\"CE Loss Recovered: {trainer.metrics['ce_loss_score']}\")\n```\n\n### Key Hyperparameters\n\n| Parameter | Typical Value | Effect |\n|-----------|---------------|--------|\n| `d_sae` | 4-16× d_model | More features, higher capacity |\n| `l1_coefficient` | 5e-5 to 1e-4 | Higher = sparser, less accurate |\n| `lr` | 1e-4 to 1e-3 | Standard optimizer LR |\n| `l1_warm_up_steps` | 500-2000 | Prevents early feature death |\n\n### Evaluation Metrics\n\n| Metric | Target | Meaning |\n|--------|--------|---------|\n| **L0** | 50-200 | Average active features per token |\n| **CE Loss Score** | 80-95% | Cross-entropy recovered vs original |\n| **Dead Features** | \u003C5% | Features that never activate |\n| **Explained Variance** | >90% | Reconstruction quality |\n\n### Checklist\n- [ ] Choose target layer and hook point\n- [ ] Set expansion factor (d_sae = 4-16× d_model)\n- [ ] Tune L1 coefficient for desired sparsity\n- [ ] Enable L1 warm-up to prevent dead features\n- [ ] Monitor metrics during training (W&B)\n- [ ] Validate L0 and CE loss recovery\n- [ ] Check dead feature ratio\n\n## Workflow 3: Feature Analysis and Steering\n\n### Analyzing Individual Features\n\n```python\nfrom transformer_lens import HookedTransformer\nfrom sae_lens import SAE\nimport torch\n\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\", device=\"cuda\")\nsae, _, _ = SAE.from_pretrained(\n    release=\"gpt2-small-res-jb\",\n    sae_id=\"blocks.8.hook_resid_pre\",\n    device=\"cuda\"\n)\n\n# Find what activates a specific feature\nfeature_idx = 1234\ntest_texts = [\n    \"The scientist conducted an experiment\",\n    \"I love chocolate cake\",\n    \"The code compiles successfully\",\n    \"Paris is beautiful in spring\",\n]\n\nfor text in test_texts:\n    tokens = model.to_tokens(text)\n    _, cache = model.run_with_cache(tokens)\n    features = sae.encode(cache[\"resid_pre\", 8])\n    activation = features[0, :, feature_idx].max().item()\n    print(f\"{activation:.3f}: {text}\")\n```\n\n### Feature Steering\n\n```python\ndef steer_with_feature(model, sae, prompt, feature_idx, strength=5.0):\n    \"\"\"Add SAE feature direction to residual stream.\"\"\"\n    tokens = model.to_tokens(prompt)\n\n    # Get feature direction from decoder\n    feature_direction = sae.W_dec[feature_idx]  # [d_model]\n\n    def steering_hook(activation, hook):\n        # Add scaled feature direction at all positions\n        activation += strength * feature_direction\n        return activation\n\n    # Generate with steering\n    output = model.generate(\n        tokens,\n        max_new_tokens=50,\n        fwd_hooks=[(\"blocks.8.hook_resid_pre\", steering_hook)]\n    )\n    return model.to_string(output[0])\n```\n\n### Feature Attribution\n\n```python\n# Which features most affect a specific output?\ntokens = model.to_tokens(\"The capital of France is\")\n_, cache = model.run_with_cache(tokens)\n\n# Get features at final position\nfeatures = sae.encode(cache[\"resid_pre\", 8])[0, -1]  # [d_sae]\n\n# Get logit attribution per feature\n# Feature contribution = feature_activation × decoder_weight × unembedding\nW_dec = sae.W_dec  # [d_sae, d_model]\nW_U = model.W_U    # [d_model, vocab]\n\n# Contribution to \"Paris\" logit\nparis_token = model.to_single_token(\" Paris\")\nfeature_contributions = features * (W_dec @ W_U[:, paris_token])\n\ntop_features = feature_contributions.topk(10)\nprint(\"Top features for 'Paris' prediction:\")\nfor idx, val in zip(top_features.indices, top_features.values):\n    print(f\"  Feature {idx.item()}: {val.item():.3f}\")\n```\n\n## Common Issues & Solutions\n\n### Issue: High dead feature ratio\n```python\n# WRONG: No warm-up, features die early\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=1e-4,\n    l1_warm_up_steps=0,  # Bad!\n)\n\n# RIGHT: Warm-up L1 penalty\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=8e-5,\n    l1_warm_up_steps=1000,  # Gradually increase\n    use_ghost_grads=True,   # Revive dead features\n)\n```\n\n### Issue: Poor reconstruction (low CE recovery)\n```python\n# Reduce sparsity penalty\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=5e-5,  # Lower = better reconstruction\n    d_sae=768 * 16,       # More capacity\n)\n```\n\n### Issue: Features not interpretable\n```python\n# Increase sparsity (higher L1)\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=1e-4,  # Higher = sparser, more interpretable\n)\n# Or use TopK architecture\ncfg = LanguageModelSAERunnerConfig(\n    architecture=\"topk\",\n    activation_fn_kwargs={\"k\": 50},  # Exactly 50 active features\n)\n```\n\n### Issue: Memory errors during training\n```python\ncfg = LanguageModelSAERunnerConfig(\n    train_batch_size_tokens=2048,  # Reduce batch size\n    store_batch_size_prompts=4,    # Fewer prompts in buffer\n    n_batches_in_buffer=8,         # Smaller activation buffer\n)\n```\n\n## Integration with Neuronpedia\n\nBrowse pre-trained SAE features at [neuronpedia.org](https:\u002F\u002Fneuronpedia.org):\n\n```python\n# Features are indexed by SAE ID\n# Example: gpt2-small layer 8 feature 1234\n# → neuronpedia.org\u002Fgpt2-small\u002F8-res-jb\u002F1234\n```\n\n## Key Classes Reference\n\n| Class | Purpose |\n|-------|---------|\n| `SAE` | Sparse Autoencoder model |\n| `LanguageModelSAERunnerConfig` | Training configuration |\n| `SAETrainingRunner` | Training loop manager |\n| `ActivationsStore` | Activation collection and batching |\n| `HookedSAETransformer` | TransformerLens + SAE integration |\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 SAE, TrainingSAE, configurations |\n| [references\u002Ftutorials.md](references\u002Ftutorials.md) | Step-by-step tutorials for training, analysis, steering |\n\n## External Resources\n\n### Tutorials\n- [Basic Loading & Analysis](https:\u002F\u002Fgithub.com\u002FjbloomAus\u002FSAELens\u002Fblob\u002Fmain\u002Ftutorials\u002Fbasic_loading_and_analysing.ipynb)\n- [Training a Sparse Autoencoder](https:\u002F\u002Fgithub.com\u002FjbloomAus\u002FSAELens\u002Fblob\u002Fmain\u002Ftutorials\u002Ftraining_a_sparse_autoencoder.ipynb)\n- [ARENA SAE Curriculum](https:\u002F\u002Fwww.lesswrong.com\u002Fposts\u002FLnHowHgmrMbWtpkxx\u002Fintro-to-superposition-and-sparse-autoencoders-colab)\n\n### Papers\n- [Towards Monosemanticity](https:\u002F\u002Ftransformer-circuits.pub\u002F2023\u002Fmonosemantic-features) - Anthropic (2023)\n- [Scaling Monosemanticity](https:\u002F\u002Ftransformer-circuits.pub\u002F2024\u002Fscaling-monosemanticity\u002F) - Anthropic (2024)\n- [Sparse Autoencoders Find Highly Interpretable Features](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.08600) - Cunningham et al. (ICLR 2024)\n\n### Official Documentation\n- [SAELens Docs](https:\u002F\u002Fjbloomaus.github.io\u002FSAELens\u002F)\n- [Neuronpedia](https:\u002F\u002Fneuronpedia.org) - Feature browser\n\n## SAE Architectures\n\n| Architecture | Description | Use Case |\n|--------------|-------------|----------|\n| **Standard** | ReLU + L1 penalty | General purpose |\n| **Gated** | Learned gating mechanism | Better sparsity control |\n| **TopK** | Exactly K active features | Consistent sparsity |\n\n```python\n# TopK SAE (exactly 50 features active)\ncfg = LanguageModelSAERunnerConfig(\n    architecture=\"topk\",\n    activation_fn=\"topk\",\n    activation_fn_kwargs={\"k\": 50},\n)\n```\n","# SAELens: Sparse Autoencoders for Mechanistic Interpretability\n\nSAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing polysemantic neural network activations into sparse, interpretable features. Based on Anthropic's groundbreaking research on monosemanticity.\n\n**GitHub**: [jbloomAus\u002FSAELens](https:\u002F\u002Fgithub.com\u002FjbloomAus\u002FSAELens) (1,100+ stars)\n\n## The Problem: Polysemanticity & Superposition\n\nIndividual neurons in neural networks are **polysemantic** - they activate in multiple, semantically distinct contexts. This happens because models use **superposition** to represent more features than they have neurons, making interpretability difficult.\n\n**SAEs solve this** by decomposing dense activations into sparse, monosemantic features - typically only a small number of features activate for any given input, and each feature corresponds to an interpretable concept.\n\n## When to Use SAELens\n\n**Use SAELens when you need to:**\n- Discover interpretable features in model activations\n- Understand what concepts a model has learned\n- Study superposition and feature geometry\n- Perform feature-based steering or ablation\n- Analyze safety-relevant features (deception, bias, harmful content)\n\n**Consider alternatives when:**\n- You need basic activation analysis → Use **TransformerLens** directly\n- You want causal intervention experiments → Use **pyvene** or **TransformerLens**\n- You need production steering → Consider direct activation engineering\n\n## Installation\n\n```bash\npip install sae-lens\n```\n\nRequirements: Python 3.10+, transformer-lens>=2.0.0\n\n## Core Concepts\n\n### What SAEs Learn\n\nSAEs are trained to reconstruct model activations through a sparse bottleneck:\n\n```\nInput Activation → Encoder → Sparse Features → Decoder → Reconstructed Activation\n    (d_model)       ↓        (d_sae >> d_model)    ↓         (d_model)\n                 sparsity                      reconstruction\n                 penalty                          loss\n```\n\n**Loss Function**: `MSE(original, reconstructed) + L1_coefficient × L1(features)`\n\n### Key Validation (Anthropic Research)\n\nIn \"Towards Monosemanticity\", human evaluators found **70% of SAE features genuinely interpretable**. Features discovered include:\n- DNA sequences, legal language, HTTP requests\n- Hebrew text, nutrition statements, code syntax\n- Sentiment, named entities, grammatical structures\n\n## Workflow 1: Loading and Analyzing Pre-trained SAEs\n\n### Step-by-Step\n\n```python\nfrom transformer_lens import HookedTransformer\nfrom sae_lens import SAE\n\n# 1. Load model and pre-trained SAE\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\", device=\"cuda\")\nsae, cfg_dict, sparsity = SAE.from_pretrained(\n    release=\"gpt2-small-res-jb\",\n    sae_id=\"blocks.8.hook_resid_pre\",\n    device=\"cuda\"\n)\n\n# 2. Get model activations\ntokens = model.to_tokens(\"The capital of France is Paris\")\n_, cache = model.run_with_cache(tokens)\nactivations = cache[\"resid_pre\", 8]  # [batch, pos, d_model]\n\n# 3. Encode to SAE features\nsae_features = sae.encode(activations)  # [batch, pos, d_sae]\nprint(f\"Active features: {(sae_features > 0).sum()}\")\n\n# 4. Find top features for each position\nfor pos in range(tokens.shape[1]):\n    top_features = sae_features[0, pos].topk(5)\n    token = model.to_str_tokens(tokens[0, pos:pos+1])[0]\n    print(f\"Token '{token}': features {top_features.indices.tolist()}\")\n\n# 5. Reconstruct activations\nreconstructed = sae.decode(sae_features)\nreconstruction_error = (activations - reconstructed).norm()\n```\n\n### Available Pre-trained SAEs\n\n| Release | Model | Layers |\n|---------|-------|--------|\n| `gpt2-small-res-jb` | GPT-2 Small | Multiple residual streams |\n| `gemma-2b-res` | Gemma 2B | Residual streams |\n| Various on HuggingFace | Search tag `saelens` | Various |\n\n### Checklist\n- [ ] Load model with TransformerLens\n- [ ] Load matching SAE for target layer\n- [ ] Encode activations to sparse features\n- [ ] Identify top-activating features per token\n- [ ] Validate reconstruction quality\n\n## Workflow 2: Training a Custom SAE\n\n### Step-by-Step\n\n```python\nfrom sae_lens import SAE, LanguageModelSAERunnerConfig, SAETrainingRunner\n\n# 1. Configure training\ncfg = LanguageModelSAERunnerConfig(\n    # Model\n    model_name=\"gpt2-small\",\n    hook_name=\"blocks.8.hook_resid_pre\",\n    hook_layer=8,\n    d_in=768,  # Model dimension\n\n    # SAE architecture\n    architecture=\"standard\",  # or \"gated\", \"topk\"\n    d_sae=768 * 8,  # Expansion factor of 8\n    activation_fn=\"relu\",\n\n    # Training\n    lr=4e-4,\n    l1_coefficient=8e-5,  # Sparsity penalty\n    l1_warm_up_steps=1000,\n    train_batch_size_tokens=4096,\n    training_tokens=100_000_000,\n\n    # Data\n    dataset_path=\"monology\u002Fpile-uncopyrighted\",\n    context_size=128,\n\n    # Logging\n    log_to_wandb=True,\n    wandb_project=\"sae-training\",\n\n    # Checkpointing\n    checkpoint_path=\"checkpoints\",\n    n_checkpoints=5,\n)\n\n# 2. Train\ntrainer = SAETrainingRunner(cfg)\nsae = trainer.run()\n\n# 3. Evaluate\nprint(f\"L0 (avg active features): {trainer.metrics['l0']}\")\nprint(f\"CE Loss Recovered: {trainer.metrics['ce_loss_score']}\")\n```\n\n### Key Hyperparameters\n\n| Parameter | Typical Value | Effect |\n|-----------|---------------|--------|\n| `d_sae` | 4-16× d_model | More features, higher capacity |\n| `l1_coefficient` | 5e-5 to 1e-4 | Higher = sparser, less accurate |\n| `lr` | 1e-4 to 1e-3 | Standard optimizer LR |\n| `l1_warm_up_steps` | 500-2000 | Prevents early feature death |\n\n### Evaluation Metrics\n\n| Metric | Target | Meaning |\n|--------|--------|---------|\n| **L0** | 50-200 | Average active features per token |\n| **CE Loss Score** | 80-95% | Cross-entropy recovered vs original |\n| **Dead Features** | \u003C5% | Features that never activate |\n| **Explained Variance** | >90% | Reconstruction quality |\n\n### Checklist\n- [ ] Choose target layer and hook point\n- [ ] Set expansion factor (d_sae = 4-16× d_model)\n- [ ] Tune L1 coefficient for desired sparsity\n- [ ] Enable L1 warm-up to prevent dead features\n- [ ] Monitor metrics during training (W&B)\n- [ ] Validate L0 and CE loss recovery\n- [ ] Check dead feature ratio\n\n## Workflow 3: Feature Analysis and Steering\n\n### Analyzing Individual Features\n\n```python\nfrom transformer_lens import HookedTransformer\nfrom sae_lens import SAE\nimport torch\n\nmodel = HookedTransformer.from_pretrained(\"gpt2-small\", device=\"cuda\")\nsae, _, _ = SAE.from_pretrained(\n    release=\"gpt2-small-res-jb\",\n    sae_id=\"blocks.8.hook_resid_pre\",\n    device=\"cuda\"\n)\n\n# Find what activates a specific feature\nfeature_idx = 1234\ntest_texts = [\n    \"The scientist conducted an experiment\",\n    \"I love chocolate cake\",\n    \"The code compiles successfully\",\n    \"Paris is beautiful in spring\",\n]\n\nfor text in test_texts:\n    tokens = model.to_tokens(text)\n    _, cache = model.run_with_cache(tokens)\n    features = sae.encode(cache[\"resid_pre\", 8])\n    activation = features[0, :, feature_idx].max().item()\n    print(f\"{activation:.3f}: {text}\")\n```\n\n### Feature Steering\n\n```python\ndef steer_with_feature(model, sae, prompt, feature_idx, strength=5.0):\n    \"\"\"Add SAE feature direction to residual stream.\"\"\"\n    tokens = model.to_tokens(prompt)\n\n    # Get feature direction from decoder\n    feature_direction = sae.W_dec[feature_idx]  # [d_model]\n\n    def steering_hook(activation, hook):\n        # Add scaled feature direction at all positions\n        activation += strength * feature_direction\n        return activation\n\n    # Generate with steering\n    output = model.generate(\n        tokens,\n        max_new_tokens=50,\n        fwd_hooks=[(\"blocks.8.hook_resid_pre\", steering_hook)]\n    )\n    return model.to_string(output[0])\n```\n\n### Feature Attribution\n\n```python\n# Which features most affect a specific output?\ntokens = model.to_tokens(\"The capital of France is\")\n_, cache = model.run_with_cache(tokens)\n\n# Get features at final position\nfeatures = sae.encode(cache[\"resid_pre\", 8])[0, -1]  # [d_sae]\n\n# Get logit attribution per feature\n# Feature contribution = feature_activation × decoder_weight × unembedding\nW_dec = sae.W_dec  # [d_sae, d_model]\nW_U = model.W_U    # [d_model, vocab]\n\n# Contribution to \"Paris\" logit\nparis_token = model.to_single_token(\" Paris\")\nfeature_contributions = features * (W_dec @ W_U[:, paris_token])\n\ntop_features = feature_contributions.topk(10)\nprint(\"Top features for 'Paris' prediction:\")\nfor idx, val in zip(top_features.indices, top_features.values):\n    print(f\"  Feature {idx.item()}: {val.item():.3f}\")\n```\n\n## Common Issues & Solutions\n\n### Issue: High dead feature ratio\n```python\n# WRONG: No warm-up, features die early\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=1e-4,\n    l1_warm_up_steps=0,  # Bad!\n)\n\n# RIGHT: Warm-up L1 penalty\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=8e-5,\n    l1_warm_up_steps=1000,  # Gradually increase\n    use_ghost_grads=True,   # Revive dead features\n)\n```\n\n### Issue: Poor reconstruction (low CE recovery)\n```python\n# Reduce sparsity penalty\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=5e-5,  # Lower = better reconstruction\n    d_sae=768 * 16,       # More capacity\n)\n```\n\n### Issue: Features not interpretable\n```python\n# Increase sparsity (higher L1)\ncfg = LanguageModelSAERunnerConfig(\n    l1_coefficient=1e-4,  # Higher = sparser, more interpretable\n)\n# Or use TopK architecture\ncfg = LanguageModelSAERunnerConfig(\n    architecture=\"topk\",\n    activation_fn_kwargs={\"k\": 50},  # Exactly 50 active features\n)\n```\n\n### Issue: Memory errors during training\n```python\ncfg = LanguageModelSAERunnerConfig(\n    train_batch_size_tokens=2048,  # Reduce batch size\n    store_batch_size_prompts=4,    # Fewer prompts in buffer\n    n_batches_in_buffer=8,         # Smaller activation buffer\n)\n```\n\n## Integration with Neuronpedia\n\nBrowse pre-trained SAE features at [neuronpedia.org](https:\u002F\u002Fneuronpedia.org):\n\n```python\n# Features are indexed by SAE ID\n# Example: gpt2-small layer 8 feature 1234\n# → neuronpedia.org\u002Fgpt2-small\u002F8-res-jb\u002F1234\n```\n\n## Key Classes Reference\n\n| Class | Purpose |\n|-------|---------|\n| `SAE` | Sparse Autoencoder model |\n| `LanguageModelSAERunnerConfig` | Training configuration |\n| `SAETrainingRunner` | Training loop manager |\n| `ActivationsStore` | Activation collection and batching |\n| `HookedSAETransformer` | TransformerLens + SAE integration |\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 SAE, TrainingSAE, configurations |\n| [references\u002Ftutorials.md](references\u002Ftutorials.md) | Step-by-step tutorials for training, analysis, steering |\n\n## External Resources\n\n### Tutorials\n- [Basic Loading & Analysis](https:\u002F\u002Fgithub.com\u002FjbloomAus\u002FSAELens\u002Fblob\u002Fmain\u002Ftutorials\u002Fbasic_loading_and_analysing.ipynb)\n- [Training a Sparse Autoencoder](https:\u002F\u002Fgithub.com\u002FjbloomAus\u002FSAELens\u002Fblob\u002Fmain\u002Ftutorials\u002Ftraining_a_sparse_autoencoder.ipynb)\n- [ARENA SAE Curriculum](https:\u002F\u002Fwww.lesswrong.com\u002Fposts\u002FLnHowHgmrMbWtpkxx\u002Fintro-to-superposition-and-sparse-autoencoders-colab)\n\n### Papers\n- [Towards Monosemanticity](https:\u002F\u002Ftransformer-circuits.pub\u002F2023\u002Fmonosemantic-features) - Anthropic (2023)\n- [Scaling Monosemanticity](https:\u002F\u002Ftransformer-circuits.pub\u002F2024\u002Fscaling-monosemanticity\u002F) - Anthropic (2024)\n- [Sparse Autoencoders Find Highly Interpretable Features](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.08600) - Cunningham et al. (ICLR 2024)\n\n### Official Documentation\n- [SAELens Docs](https:\u002F\u002Fjbloomaus.github.io\u002FSAELens\u002F)\n- [Neuronpedia](https:\u002F\u002Fneuronpedia.org) - Feature browser\n\n## SAE Architectures\n\n| Architecture | Description | Use Case |\n|--------------|-------------|----------|\n| **Standard** | ReLU + L1 penalty | General purpose |\n| **Gated** | Learned gating mechanism | Better sparsity control |\n| **TopK** | Exactly K active features | Consistent sparsity |\n\n```python\n# TopK SAE (exactly 50 features active)\ncfg = LanguageModelSAERunnerConfig(\n    architecture=\"topk\",\n    activation_fn=\"topk\",\n    activation_fn_kwargs={\"k\": 50},\n)\n```\n",{"name":5,"tags":24,"author":30,"license":15,"version":31,"description":7,"dependencies":32},[25,26,27,28,29],"Sparse Autoencoders","SAE","Mechanistic Interpretability","Feature Discovery","Superposition","Orchestra Research","1.0.0",[33,34,35],"sae-lens>=6.0.0","transformer-lens>=2.0.0","torch>=2.0.0","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fai-research-skills\u002F04-mechanistic-interpretability\u002Fsaelens",0,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science","https:\u002F\u002Fgithub.com\u002FCZX-LBJ","一个没事喜欢随便写点代码的小菜鸡\r\n","2026-10-22 09:48:04",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add CZX-LBJ\u002Fdeepseek-science --skill sparse-autoencoder-training",{"tool":50,"command":51},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill sparse-autoencoder-training",{"tool":53,"command":54},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill sparse-autoencoder-training","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fai-research-skills\u002F04-mechanistic-interpretability\u002Fsaelens\u002FSKILL.md",true,[58,64,68],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fapi.md","REFERENCE","参考文档",6968,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fai-research-skills\u002F04-mechanistic-interpretability\u002Fsaelens\u002Freferences\u002Fapi.md",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002FREADME.md",2155,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fai-research-skills\u002F04-mechanistic-interpretability\u002Fsaelens\u002Freferences\u002FREADME.md",{"path":69,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Ftutorials.md",9383,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fai-research-skills\u002F04-mechanistic-interpretability\u002Fsaelens\u002Freferences\u002Ftutorials.md",[73,80,87,94,101,108],{"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},"01M7FEEKSNMRMKW6JEK93PFDFY","bio-free-energy-calculations","Performs alchemical free-energy calculations including relative binding free energy (RBFE \u002F FEP+) and absolute binding free energy (ABFE) via OpenFE, FEP+, GROMACS, AMBER pmemd, and OpenMM with explicit lambda scheduling, soft-core potentials, MBAR\u002FBAR analysis, cycle-closure validation, and protocol-appropriate enhanced sampling. Compares ML alternatives (Boltz-2 affinity, DeepDock). Use when ranking analogs by binding affinity beyond docking accuracy, performing prospective lead optimization, or validating SAR predictions.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Ffree-energy-calculations\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":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7FEE5CTE5QK55CEMXNNVWY9","bio-conformer-generation","Generates 3D conformer ensembles using RDKit ETKDGv3 with knowledge-enhanced distance geometry, MMFF94\u002FUFF force-field optimization, CREST + GFN2-xTB semi-empirical refinement, and macrocycle-aware torsion preferences. Provides explicit decision rules for single vs ensemble conformer use, RMSD pruning, energy windows, conformer count, and force-field choice. Use when preparing 3D ligands for docking, generating descriptor input for 3D QSAR, or sampling macrocycle\u002Fpeptide conformational ensembles.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fconformer-generation\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7FEDNGFEMFWD1MSEDR5H7CY","bio-admet-prediction","Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG\u002FCYP\u002FAMES endpoints, and PAINS \u002F Lipinski \u002F Ro5 \u002F Veber \u002F BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fadmet-prediction\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7FED69GFB54FRF7AV5066DN","writing-systems-papers","Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says \"写系统论文\", \"systems paper structure\", \"OSDI paper\", \"SOSP paper\", or wants fine-grained structural guidance for a systems conference submission.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwriting-systems-papers\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7FECVVDWZ0X0VEDTCE4B4DZ","wiki-enrich","Fill in the per-paper TODO sections of research-wiki\u002Fpapers\u002F\u003Cslug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers\u002F as TODO scaffolds.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwiki-enrich\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M7FECD4BCJ2MTSBDDSE3ZAJ5","web-debug-search","Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-world workarounds. Use for debugging and discovery only; results are not paper-citation evidence.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fweb-debug-search\u002FSKILL.md",[],[]]