TransluceAI / observatoryLinks
A toolkit for describing model features and intervening on those features to steer behavior.
☆184Updated 6 months ago
Alternatives and similar repositories for observatory
Users that are interested in observatory are comparing it to the libraries listed below
Sorting:
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆180Updated this week
- Mechanistic Interpretability Visualizations using React☆251Updated 5 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆200Updated 5 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆101Updated 3 months ago
- ☆170Updated last month
- ☆120Updated 6 months ago
- Using sparse coding to find distributed representations used by neural networks.☆247Updated last year
- Open source interpretability artefacts for R1.☆138Updated last month
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆223Updated 8 months ago
- ☆222Updated 8 months ago
- ☆121Updated last year
- ☆156Updated 6 months ago
- ☆130Updated 2 months ago
- open source interpretability platform 🧠☆131Updated this week
- ☆96Updated 3 months ago
- Sparsify transformers with SAEs and transcoders☆547Updated this week
- Improving Alignment and Robustness with Circuit Breakers☆207Updated 8 months ago
- ☆174Updated last month
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- ☆116Updated 9 months ago
- ☆96Updated last month
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆115Updated this week
- Steering Llama 2 with Contrastive Activation Addition☆154Updated last year
- ☆39Updated 3 weeks ago
- ☆152Updated 2 months ago
- METR Task Standard☆147Updated 3 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 6 months ago
- ☆42Updated 6 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆248Updated 10 months ago