neelnanda-io / 1L-Sparse-AutoencoderLinks
☆121Updated 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).☆200Updated 5 months ago
- ☆222Updated 7 months ago
- Using sparse coding to find distributed representations used by neural networks.☆247Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆180Updated this week
- ☆302Updated last week
- ☆170Updated last month
- Sparse Autoencoder Training Library☆50Updated 3 weeks ago
- Mechanistic Interpretability Visualizations using React☆251Updated 5 months ago
- ☆42Updated 6 months ago
- ☆96Updated last month
- Sparse Autoencoder for Mechanistic Interpretability☆248Updated 10 months ago
- ☆120Updated 6 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆101Updated 3 months ago
- Sparse probing paper full code.☆56Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆125Updated 2 years ago
- ☆93Updated 3 months ago
- Attribution-based Parameter Decomposition☆21Updated last week
- ☆116Updated 9 months ago
- ☆39Updated 3 weeks ago
- ☆27Updated last year
- ☆83Updated 9 months ago
- An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"☆45Updated last year
- ☆66Updated 2 years ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆74Updated 6 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆33Updated last year
- Sparsify transformers with SAEs and transcoders☆547Updated this week
- Tools for studying developmental interpretability in neural networks.☆90Updated 4 months ago
- Steering Llama 2 with Contrastive Activation Addition☆154Updated last year