evan-lloyd / graphpatchLinks
graphpatch is a library for activation patching on PyTorch neural network models.
☆14Updated 3 months ago
Alternatives and similar repositories for graphpatch
Users that are interested in graphpatch are comparing it to the libraries listed below
Sorting:
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Updated 8 months ago
- Sparse Autoencoder Training Library☆52Updated last month
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- ☆34Updated 2 weeks ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆201Updated 5 months ago
- ☆121Updated last year
- ☆28Updated last year
- ☆28Updated 10 months ago
- Attribution-based Parameter Decomposition☆24Updated this week
- ☆75Updated 3 months ago
- ☆33Updated 4 months ago
- Erasing concepts from neural representations with provable guarantees☆228Updated 4 months ago
- A library for mechanistic anomaly detection☆21Updated 4 months ago
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- ☆96Updated 3 months ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆43Updated 6 months ago
- ☆94Updated 3 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆181Updated this week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆126Updated 2 years ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- ☆97Updated last month
- ☆9Updated 6 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 4 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆34Updated last year
- ☆26Updated 2 years ago
- Modified to support crosscoder training.☆17Updated this week
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆27Updated last year
- ☆304Updated 2 weeks ago
- ☆31Updated last year
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆17Updated 7 months ago