bartbussmann / matryoshka_saeLinks
☆48Updated 9 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:
- ☆108Updated 8 months ago
- ☆131Updated last week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆219Updated last week
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆83Updated 11 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆26Updated 8 months ago
- ☆191Updated 2 weeks ago
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆43Updated last year
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆136Updated 4 months ago
- ☆23Updated 11 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated last year
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)☆51Updated 3 months ago
- Modified to support crosscoder training.☆24Updated 3 weeks ago
- ☆74Updated 2 weeks ago
- ☆54Updated 11 months ago
- ☆181Updated 11 months ago
- ☆18Updated 2 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆126Updated 8 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆25Updated 11 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆40Updated 11 months ago
- ☆16Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆280Updated last year
- ☆23Updated 9 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆224Updated 10 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆276Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆181Updated 6 months ago
- Attribution-based Parameter Decomposition☆31Updated 4 months ago
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆14Updated 2 weeks ago