bartbussmann / matryoshka_saeLinks
☆38Updated 6 months ago
Alternatives and similar repositories for matryoshka_sae
Users that are interested in matryoshka_sae are comparing it to the libraries listed below
Sorting:
- ☆109Updated 3 weeks ago
- ☆103Updated 5 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆202Updated this week
- ☆183Updated 3 weeks ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆120Updated 5 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆112Updated last month
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆73Updated 2 weeks ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆52Updated 10 months ago
- ☆15Updated 2 months ago
- Steering Llama 2 with Contrastive Activation Addition☆167Updated last year
- ☆121Updated last year
- ☆51Updated 8 months ago
- ☆21Updated 8 months ago
- ☆234Updated 10 months ago
- Using sparse coding to find distributed representations used by neural networks.☆261Updated last year
- ☆157Updated 8 months ago
- ☆89Updated last year
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆23Updated 5 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 8 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆257Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆175Updated 3 months ago
- ☆324Updated 3 weeks ago
- Attribution-based Parameter Decomposition☆28Updated last month
- ☆64Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- ☆23Updated 6 months ago