Agent Skills: mechanistic-interpretability-pyvene

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.

ID: davila7/claude-code-templates/mechanistic-interpretability-pyvene

Install this agent skill to your local

npx skills add davila7/claude-code-templates --skill mechanistic-interpretability-pyvene

Skill Files

The files that make up mechanistic-interpretability-pyvene.

Download Skill

More agent skills