pyvene-interventions
Category: ml-evaluation-and-safety · License: MIT · Version: 1.0.0
Tags: Causal Intervention, pyvene, Activation Patching, Causal Tracing, Interpretability
When to use it
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.Example requests
Ask your agent in plain language, for example:- “How do I do activation patching with pyvene on GPT-2?”
- “I’m replicating ROME-style causal tracing on gpt2-xl for the prompt ‘The Space Needle is located in the city of’. I corrupted the subject tokens with Gaussian noise, and now I want to restore the clean hidden state at each (layer, token position) and plot a heatmap of the recovered probability for ’ Seattle’. I’m using pyvene and getting a dimension mismatch error when I set the intervention location. How should I set this up and fix it?”
- “I think a model represents whether a number is greater than a threshold in a low-dimensional linear subspace of one layer’s residual stream. I want to learn that subspace by training with counterfactual pairs and then test if swapping it flips the model’s output. What approach and library setup would you recommend?”
Install
/plugin marketplace add KalarisLabs/research-agent-skills and install the whole ml-evaluation-and-safety category with /plugin install ml-evaluation-and-safety@research-agent-skills.
Related
hypothesis-generationlangsmith-observabilitytransformer-lens-interpretability- Skills for machine learning research