callummcdougall / sae_visLinks
Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
☆212Updated 8 months ago
Alternatives and similar repositories for sae_vis
Users that are interested in sae_vis are comparing it to the libraries listed below
Sorting:
- ☆126Updated last year
- Mechanistic Interpretability Visualizations using React☆280Updated 8 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
- ☆238Updated 10 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆260Updated last year
- Sparsify transformers with SAEs and transcoders☆609Updated last week
- ☆327Updated this week
- ☆114Updated last month
- ☆184Updated last month
- Using sparse coding to find distributed representations used by neural networks.☆262Updated last year
- ☆29Updated last year
- ☆162Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- ☆53Updated 9 months ago
- ☆122Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆630Updated this week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆58Updated 9 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆516Updated 2 weeks ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆197Updated 9 months ago
- ☆139Updated last week
- ☆276Updated last year
- Attribution-based Parameter Decomposition☆28Updated 2 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 2 years ago
- Extract full next-token probabilities via language model APIs☆247Updated last year
- Decoder only transformer, built from scratch with PyTorch☆31Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆174Updated last year
- ☆508Updated last year
- ☆67Updated last week
- Erasing concepts from neural representations with provable guarantees☆232Updated 6 months ago