HoagyC / sparse_codingLinks
Using sparse coding to find distributed representations used by neural networks.
☆262Updated last year
Alternatives and similar repositories for sparse_coding
Users that are interested in sparse_coding are comparing it to the libraries listed below
Sorting:
- Sparse Autoencoder for Mechanistic Interpretability☆258Updated last year
- ☆237Updated 10 months ago
- ☆162Updated 9 months ago
- ☆184Updated last month
- ☆111Updated last month
- ☆327Updated this week
- Steering Llama 2 with Contrastive Activation Addition☆174Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆206Updated this week
- ☆508Updated last year
- ☆126Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆211Updated 8 months ago
- Sparsify transformers with SAEs and transcoders☆608Updated this week
- Mechanistic Interpretability Visualizations using React☆280Updated 8 months ago
- ☆122Updated last year
- ☆185Updated 9 months ago
- ☆52Updated 9 months ago
- An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"☆48Updated last year
- Sparse probing paper full code.☆59Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- This repository collects all relevant resources about interpretability in LLMs☆368Updated 9 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆58Updated 9 months ago
- Training Sparse Autoencoders on Language Models☆919Updated this week
- ☆223Updated last year
- ☆47Updated 3 weeks ago
- [ICLR 2025] General-purpose activation steering library☆94Updated 3 weeks ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆143Updated last week
- ☆103Updated 6 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆96Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆630Updated this week
- A resource repository for representation engineering in large language models☆130Updated 9 months ago