TransluceAI / observatoryLinks
A toolkit for describing model features and intervening on those features to steer behavior.
☆207Updated 11 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 …☆218Updated last week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆222Updated 10 months ago
- Open source interpretability artefacts for R1.☆161Updated 6 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 8 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆290Updated 4 months ago
- Mechanistic Interpretability Visualizations using React☆293Updated 10 months ago
- ☆179Updated 11 months ago
- ☆142Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆188Updated last year
- ☆113Updated last week
- Repository for the paper Stream of Search: Learning to Search in Language☆151Updated 8 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- Functional Benchmarks and the Reasoning Gap☆89Updated last year
- Sparsify transformers with SAEs and transcoders☆640Updated last week
- ☆190Updated last week
- ☆54Updated 11 months ago
- ☆126Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆94Updated last year
- ☆247Updated last year
- ☆131Updated this week
- Improving Alignment and Robustness with Circuit Breakers☆238Updated last year
- ☆36Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆136Updated 3 months ago
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆291Updated 2 weeks ago
- Extract full next-token probabilities via language model APIs☆247Updated last year
- Sparse Autoencoder for Mechanistic Interpretability☆272Updated last year
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆233Updated 3 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆157Updated this week