菜单
Use this skill when working with Sparse Autoencoders (SAEs) for mechanistic interpretability of language models, including training SAEs, loading pre-trained SAEs, analyzing neural network features, or integrating SAEs with TransformerLens, HuggingFace Transformers, or other PyTorch-based models.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/zjunlp/Mechanist --skill saelens命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
The single place for every data constraint an experiment must satisfy — dataset provenance (existing → adapted → constructed), clear train / validation / test splits, labels that reflect the target behavior, and the minimum data amount. Use whenever an experiment chooses, adapts, or constructs a dataset, defines splits, or sets a sample size — for phenomenon validation (M0), mechanism exploration, intervention, or tuning. Domain-general: no assumption about model family, modality, or task.
Autonomous research review loop that consumes /auto-verify's four-state output (PASS / FAIL / INCONCLUSIVE / ZERO_ELIGIBLE_VARIANTS / deferred) and routes each claim to the right back-edge — brief audit, two-phase FAIL handling (variant-integrity fix then optional claim-stage re-entry), main-experiment-script fix, or variant-only fix — under a unified iteration budget. Configure the reviewer LLM via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
Autonomous pipeline: claim → experiment (mechanism routing folded in) → verify → iteration. Each stage is delegated to an isolated agent with its own context window and configurable model. Gates are AUTO_PROCEED-governed; defaults run end-to-end without human input. Use when user says "auto pipeline", or wants the core stages chained without confirmation.
| name | saelens |
| description | Use this skill when working with Sparse Autoencoders (SAEs) for mechanistic interpretability of language models, including training SAEs, loading pre-trained SAEs, analyzing neural network features, or integrating SAEs with TransformerLens, HuggingFace Transformers, or other PyTorch-based models. |
Activate this skill when:
Keywords: sparse autoencoder, SAE, mechanistic interpretability, TransformerLens, feature analysis, neural network features, activation patching, SAE training, HookedSAETransformer, Neuronpedia, dictionary learning, GPT-2, language model interpretability
pip install sae-lens
git clone https://github.com/decoderesearch/SAELens.git
cd SAELens
pip install -e ".[dev]"