TransluceAI / observatoryLinks
A toolkit for describing model features and intervening on those features to steer behavior.
☆203Updated 10 months ago
Alternatives and similar repositories for observatory
Users that are interested in observatory are comparing it to the libraries listed below
Sorting:
- Open source interpretability artefacts for R1.☆159Updated 5 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆213Updated last week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- Mechanistic Interpretability Visualizations using React☆289Updated 9 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆275Updated 3 months ago
- ☆142Updated 3 weeks ago
- ☆102Updated 5 months ago
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆281Updated this week
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆154Updated this week
- Extract full next-token probabilities via language model APIs☆248Updated last year
- ☆173Updated 10 months ago
- Sparsify transformers with SAEs and transcoders☆629Updated this week
- ☆242Updated last year
- A simple unified framework for evaluating LLMs☆248Updated 5 months ago
- ☆123Updated last year
- open source interpretability platform 🧠☆425Updated this week
- ☆54Updated 10 months ago
- ☆186Updated 2 months ago
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆230Updated 2 months ago
- ☆125Updated 2 weeks ago
- METR Task Standard☆161Updated 7 months ago
- Steering Llama 2 with Contrastive Activation Addition☆182Updated last year
- Sparse Autoencoder for Mechanistic Interpretability☆267Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆80Updated 10 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- Sparse Autoencoder Training Library☆54Updated 5 months ago
- Functional Benchmarks and the Reasoning Gap☆89Updated last year
- Repository for the paper Stream of Search: Learning to Search in Language☆151Updated 8 months ago