redwoodresearch / interp
Redwood Research's transformer interpretability tools
☆14Updated 2 years ago
Alternatives and similar repositories for interp:
Users that are interested in interp are comparing it to the libraries listed below
- Mechanistic Interpretability for Transformer Models☆49Updated 2 years ago
- ☆19Updated 2 years ago
- ☆60Updated 3 months ago
- A library for efficient patching and automatic circuit discovery.☆56Updated 3 weeks ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 9 months ago
- ☆60Updated last month
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆15Updated 3 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- ☆26Updated 11 months ago
- we got you bro☆35Updated 7 months ago
- Sparse Autoencoder Training Library☆42Updated 4 months ago
- Scaling scaling laws with board games.☆48Updated last year
- ☆41Updated last month
- Tools for studying developmental interpretability in neural networks.☆86Updated last month
- ☆52Updated 5 months ago
- Measuring the situational awareness of language models☆34Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆90Updated 2 weeks ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated last month
- Sparse and discrete interpretability tool for neural networks☆59Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆44Updated 4 months ago
- ☆29Updated 10 months ago
- ☆61Updated 2 years ago
- ☆112Updated 7 months ago
- ☆10Updated 8 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆29Updated 9 months ago
- ☆210Updated 5 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆72Updated last year
- 🧠 Starter templates for doing interpretability research☆66Updated last year
- Implementation of Influence Function approximations for differently sized ML models, using PyTorch☆15Updated last year