neelnanda-io / 1L-Sparse-AutoencoderLinks
☆128Updated last year
Alternatives and similar repositories for 1L-Sparse-Autoencoder
Users that are interested in 1L-Sparse-Autoencoder are comparing it to the libraries listed below
Sorting:
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆222Updated 10 months ago
- ☆247Updated last year
- Mechanistic Interpretability Visualizations using React☆293Updated 10 months ago
- ☆354Updated 2 months ago
- 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
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆272Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆279Updated last year
- ☆179Updated 11 months ago
- ☆54Updated 11 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- ☆131Updated this week
- ☆190Updated last week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- ☆126Updated last year
- ☆279Updated last year
- Attribution-based Parameter Decomposition☆31Updated 4 months ago
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- Modified to support crosscoder training.☆23Updated 2 weeks ago
- Steering Llama 2 with Contrastive Activation Addition☆188Updated last year
- ☆29Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 8 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆532Updated 2 months ago
- ☆107Updated 8 months ago
- Erasing concepts from neural representations with provable guarantees☆238Updated 8 months ago
- ☆81Updated 7 months ago
- Sparsify transformers with SAEs and transcoders☆640Updated last week
- Sparse probing paper full code.☆62Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆683Updated last week
- ☆530Updated last year