TransluceAI / observatoryLinks
A toolkit for describing model features and intervening on those features to steer behavior.
☆223Updated last week
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 …☆234Updated last week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆232Updated last year
- Open source interpretability artefacts for R1.☆165Updated 8 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆134Updated 10 months ago
- ☆74Updated this week
- Mechanistic Interpretability Visualizations using React☆303Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆316Updated 6 months ago
- ☆144Updated 3 months ago
- ☆192Updated last year
- ☆260Updated last year
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆234Updated 5 months ago
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆328Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆201Updated last year
- ☆196Updated 2 months ago
- Sparsify transformers with SAEs and transcoders☆673Updated last week
- Sparse Autoencoder for Mechanistic Interpretability☆286Updated last year
- ☆232Updated 3 weeks ago
- A library for efficient patching and automatic circuit discovery.☆82Updated 5 months ago
- Unified access to Large Language Model modules using NNsight☆70Updated last month
- open source interpretability platform 🧠☆562Updated this week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Updated last year
- ☆134Updated last year
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆168Updated this week
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆135Updated last week
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆99Updated 2 years ago
- Collection of evals for Inspect AI☆313Updated this week
- ☆136Updated last month
- METR Task Standard☆169Updated 10 months ago
- ☆124Updated 2 months ago
- ☆58Updated last year