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.
安装
npx skills add davila7/claude-code-templates --skill pyvene-interventionsnpx skills add davila7/claude-code-templates --skill pyvene-interventions -a claude-code -gnpx skills add davila7/claude-code-templates --skill pyvene-interventions -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/mechanistic-interpretability-pyvenegh skill install davila7/claude-code-templates pyvene-interventionsgit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/mechanistic-interpretability-pyvene ~/.claude/skills/pyvene-interventions # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/mechanistic-interpretability-pyvene ~/.agents/skills/pyvene-interventions # Codex, Cursor, Gemini CLI, Copilot, OpenCode