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.
安装
npx skills add NousResearch/hermes-agent --skill saelensnpx skills add NousResearch/hermes-agent --skill saelens -a claude-code -gnpx skills add NousResearch/hermes-agent --skill saelens -a codex -ggemini skills install https://github.com/NousResearch/hermes-agent.git --path optional-skills/mlops/saelensgh skill install NousResearch/hermes-agent saelensgit clone --depth 1 https://github.com/NousResearch/hermes-agent /tmp/NousResearch__hermes-agent
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NousResearch__hermes-agent/optional-skills/mlops/saelens ~/.claude/skills/saelens # Claude Code
cp -R /tmp/NousResearch__hermes-agent/optional-skills/mlops/saelens ~/.agents/skills/saelens # Codex, Cursor, Gemini CLI, Copilot, OpenCode