neelnanda-io / CrosscodersLinks
☆53Updated 9 months ago
Alternatives and similar repositories for Crosscoders
Users that are interested in Crosscoders are comparing it to the libraries listed below
Sorting:
- Open source replication of Anthropic's Crosscoders for Model Diffing☆58Updated 9 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆206Updated last week
- ☆114Updated last month
- ☆184Updated last month
- ☆162Updated 9 months ago
- ☆126Updated last year
- ☆238Updated 10 months ago
- Modified to support crosscoder training.☆22Updated 3 weeks ago
- Using sparse coding to find distributed representations used by neural networks.☆262Updated last year
- ☆327Updated this week
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆212Updated 8 months ago
- Steering Llama 2 with Contrastive Activation Addition☆174Updated last year
- ☆122Updated last year
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- ☆67Updated last week
- Sparse Autoencoder for Mechanistic Interpretability☆260Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- ☆103Updated 6 months ago
- ☆187Updated 9 months ago
- ☆32Updated last year
- ☆81Updated 6 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 9 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- Attribution-based Parameter Decomposition☆28Updated 2 months ago
- Mechanistic Interpretability Visualizations using React☆280Updated 8 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆145Updated this week
- Unified access to Large Language Model modules using NNsight☆42Updated this week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 2 years ago
- ☆90Updated last year