TransluceAI / observatoryLinks
A toolkit for describing model features and intervening on those features to steer behavior.
☆195Updated 8 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 …☆200Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆119Updated 5 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆246Updated last month
- Open source interpretability artefacts for R1.☆157Updated 3 months ago
- ☆134Updated 4 months ago
- Mechanistic Interpretability Visualizations using React☆272Updated 7 months ago
- ☆94Updated 3 months ago
- open source interpretability platform 🧠☆311Updated this week
- ☆50Updated 8 months ago
- A simple unified framework for evaluating LLMs☆229Updated 3 months ago
- Steering Llama 2 with Contrastive Activation Addition☆167Updated last year
- ☆87Updated 11 months ago
- ☆233Updated 10 months ago
- ☆154Updated 8 months ago
- Sparsify transformers with SAEs and transcoders☆595Updated this week
- Sparse Autoencoder for Mechanistic Interpretability☆257Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆217Updated last week
- Functional Benchmarks and the Reasoning Gap☆88Updated 10 months ago
- ☆183Updated 2 weeks ago
- ☆175Updated 4 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆85Updated last year
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆141Updated last week
- ☆121Updated 11 months ago
- Extract full next-token probabilities via language model APIs☆247Updated last year
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆225Updated 2 weeks ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆96Updated last year
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- Repository for the paper Stream of Search: Learning to Search in Language☆149Updated 6 months ago