jbloomAus / SAEDashboardLinks
☆66Updated last week
Alternatives and similar repositories for SAEDashboard
Users that are interested in SAEDashboard are comparing it to the libraries listed below
Sorting:
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆58Updated 9 months ago
- ☆111Updated last month
- 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
- Attribution-based Parameter Decomposition☆28Updated 2 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 8 months ago
- ☆52Updated 9 months ago
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- ☆126Updated last year
- ☆32Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆211Updated 8 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 2 years ago
- ☆138Updated 4 months ago
- ☆103Updated 6 months ago
- ☆237Updated 10 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- ☆105Updated 6 months ago
- ☆122Updated last year
- Sparse Autoencoder for Mechanistic Interpretability☆258Updated last year
- Applying SAEs for fine-grained control☆23Updated 8 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆21Updated last month
- ☆90Updated last year
- ☆184Updated last month
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆124Updated 2 months ago
- ☆28Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- Universal Neurons in GPT2 Language Models☆30Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- Engine for collecting, uploading, and downloading model activations☆22Updated 4 months ago
- ☆38Updated 7 months ago