HoagyC / sparse_coding
Using sparse coding to find distributed representations used by neural networks.
☆224Updated last year
Alternatives and similar repositories for sparse_coding:
Users that are interested in sparse_coding are comparing it to the libraries listed below
- ☆211Updated 5 months ago
- ☆255Updated last month
- Sparse Autoencoder for Mechanistic Interpretability☆233Updated 8 months ago
- ☆121Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆161Updated this week
- Mechanistic Interpretability Visualizations using React☆233Updated 3 months ago
- ☆149Updated 2 weeks ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆189Updated 3 months ago
- ☆71Updated this week
- ☆61Updated 4 months ago
- ☆113Updated 7 months ago
- Steering Llama 2 with Contrastive Activation Addition☆129Updated 10 months ago
- Training Sparse Autoencoders on Language Models☆669Updated this week
- Sparsify transformers with SAEs and transcoders☆494Updated this week
- ☆125Updated 4 months ago
- ☆89Updated last month
- Steering vectors for transformer language models in Pytorch / Huggingface☆90Updated last month
- A library for efficient patching and automatic circuit discovery.☆59Updated last month
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆91Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆45Updated 4 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆30Updated 9 months ago
- ☆195Updated last year
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆104Updated this week
- A resource repository for representation engineering in large language models☆113Updated 4 months ago
- An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"☆40Updated 10 months ago
- ☆441Updated 8 months ago
- Sparse probing paper full code.☆55Updated last year
- ☆32Updated 4 months ago
- ☆23Updated 3 weeks ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆518Updated this week