mechanistic-interpretability-pyvene

原文涵盖的主题

• pyvene: Causal Interventions for Neural Networks
• When to Use pyvene
• Installation
• Core Concepts
• IntervenableModel
• Intervention Types
• Component Targets
• Workflow 1: Causal Tracing (ROME-style)

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. GitHub: stanfordnlp/pyvene (840+ stars) Paper: pyvene: A Library for Understanding and Improving PyTorch Models via Interventions (NAACL 2024) Use pyvene when you need to: Perform causal tracing (ROME-style localization) Run activation patching experiments Conduct interchange intervention training (IIT) Test causal hypotheses about model components Share/reproduce intervention experiments via HuggingFace Work with any PyTorch architecture (not just transformers) Consider alternatives when: You need exploratory activation analysis → Use TransformerLens You want to train/analyze SAEs → Use SAELens You need remote execution on massive models → Use nnsight You want lower-level control → Use nnsight Standard import: The main class that wraps any PyTorch model with intervention capabilities: | Type | Description | Use Case | |------|-------------|----------| | VanillaIntervention | Swap activations between runs | Ac

这里只展示节选，请以完整原文和当前要求为准。