TransluceAI / docentLinks
☆81Updated last week
Alternatives and similar repositories for docent
Users that are interested in docent are comparing it to the libraries listed below
Sorting:
- A toolkit for describing model features and intervening on those features to steer behavior.☆227Updated last month
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆241Updated last week
- Mechanistic Interpretability Visualizations using React☆318Updated last year
- Unified access to Large Language Model modules using NNsight☆87Updated last week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆238Updated last year
- ☆58Updated last year
- Inference API for many LLMs and other useful tools for empirical research☆103Updated last week
- ☆132Updated 2 years ago
- ☆267Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Updated last year
- A library for efficient patching and automatic circuit discovery.☆88Updated last month
- This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix …☆121Updated 2 weeks ago
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆150Updated last week
- Attribution-based Parameter Decomposition☆33Updated 7 months ago
- ☆143Updated last month
- Steering vectors for transformer language models in Pytorch / Huggingface☆140Updated 11 months ago
- ☆206Updated 3 months ago
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆55Updated this week
- METR Task Standard☆172Updated last year
- Applying SAEs for fine-grained control☆25Updated last year
- ☆197Updated last year
- ☆83Updated 11 months ago
- Engine for collecting, uploading, and downloading model activations☆25Updated 10 months ago
- ☆152Updated 4 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆45Updated last year
- Open source interpretability artefacts for R1.☆170Updated 9 months ago
- ☆70Updated 3 weeks ago
- ☆137Updated last year
- ☆388Updated 5 months ago
- ☆133Updated 3 months ago