Overview
pyvene-interventions is an open-source testing skill for Claude Code and compatible agents, published by Orchestra-Research. Its author describes it as: “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…”. The project has 12k stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add Orchestra-Research/AI-Research-SKILLs`.
What pyvene-interventions does
pyvene is Stanford NLP's library for performing causal interventions on PyTorch models. It provides a declarative, dict-based framework for activation patching, causal tracing, and interchange intervention training - making intervention experiments reproducible and shareable.
What’s inside
The SKILL.md for pyvene-interventions is organised into these sections:
- When to Use pyvene
- Installation
- Core Concepts
- IntervenableModel
- Intervention Types
- Component Targets
- Workflow 1: Causal Tracing (ROME-style)
- Step-by-Step
- Checklist
- Workflow 2: Activation Patching for Circuit Analysis
- Workflow 3: Interchange Intervention Training (IIT)
- DAS (Distributed Alignment Search)
Installation
Add pyvene-interventions to your agent with:
/plugin marketplace add Orchestra-Research/AI-Research-SKILLsReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — ships a claude code plugin marketplace
- Codex — declared in the repository topics
License
pyvene-interventions is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in Orchestra-Research/AI-Research-SKILLs, an established project with 11,807 GitHub stars
- Works with Claude Code, Codex
Author
Topics
Frequently asked questions
- What does pyvene-interventions do?
- 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.
- How do I install pyvene-interventions?
- Run /plugin marketplace add Orchestra-Research/AI-Research-SKILLs in your agent, then reload your skills. Review the source at https://github.com/Orchestra-Research/AI-Research-SKILLs before installing.
- Is pyvene-interventions free to use?
- Yes. pyvene-interventions is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does pyvene-interventions work with?
- pyvene-interventions lists Claude Code and Codex — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does pyvene-interventions come from?
- pyvene-interventions ships inside Orchestra-Research/AI-Research-SKILLs, a repository that contains 41 catalogued skills in total. The repository's 11,807 GitHub stars apply to that whole collection, not to this skill on its own.
