neelnanda-io / Crosscoders
☆32Updated 4 months ago
Alternatives and similar repositories for Crosscoders:
Users that are interested in Crosscoders are comparing it to the libraries listed below
- Open source replication of Anthropic's Crosscoders for Model Diffing☆48Updated 5 months ago
- ☆66Updated 4 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆165Updated last week
- ☆121Updated last year
- ☆33Updated last month
- ☆80Updated this week
- A library for efficient patching and automatic circuit discovery.☆62Updated last month
- ☆264Updated last month
- Steering vectors for transformer language models in Pytorch / Huggingface☆91Updated last month
- Using sparse coding to find distributed representations used by neural networks.☆225Updated last year
- Sparse Autoencoder Training Library☆47Updated 5 months ago
- ☆90Updated last month
- ☆151Updated last week
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆17Updated 4 months ago
- Universal Neurons in GPT2 Language Models☆27Updated 10 months ago
- ☆214Updated 6 months ago
- ☆114Updated 7 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆192Updated 3 months ago
- ☆26Updated 11 months ago
- Applying SAEs for fine-grained control☆16Updated 3 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆73Updated 4 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆234Updated 8 months ago
- Algebraic value editing in pretrained language models☆63Updated last year
- ☆30Updated 11 months ago
- Mechanistic Interpretability Visualizations using React☆235Updated 3 months ago
- Steering Llama 2 with Contrastive Activation Addition☆134Updated 10 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆22Updated last month
- ☆82Updated 7 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆30Updated 10 months ago