rmovva / HypotheSAEsLinks
Hypothesizing interpretable relationships in text datasets using sparse autoencoders.
☆42Updated last week
Alternatives and similar repositories for HypotheSAEs
Users that are interested in HypotheSAEs are comparing it to the libraries listed below
Sorting:
- Discovering Data-driven Hypotheses in the Wild☆109Updated 2 months ago
- Official implementation of "BERTs are Generative In-Context Learners"☆32Updated 5 months ago
- Understanding how features learned by neural networks evolve throughout training☆37Updated 10 months ago
- ☆106Updated 6 months ago
- Code for "Counterfactual Token Generation in Large Language Models", Arxiv 2024.☆28Updated 9 months ago
- Dataset and evaluation suite enabling LLM instruction-following for scientific literature understanding.☆40Updated 5 months ago
- ☆227Updated last week
- This is the repo for constructing a comprehensive and rigorous evaluation framework for LLM calibration.☆13Updated last year
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆46Updated 9 months ago
- This is the official repository for HypoGeniC (Hypothesis Generation in Context) and HypoRefine, which are automated, data-driven tools t…☆85Updated 2 weeks ago
- A lightweight library for Bayesian analysis of LLM evals (ICML 2025 Spotlight Position Paper)☆20Updated 3 months ago
- PyTorch library for Active Fine-Tuning☆90Updated last week
- ☆48Updated 9 months ago
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)☆45Updated last month
- ☆68Updated last week
- ScienceMeter: Tracking Scientific Knowledge Updates in Language Models☆15Updated 2 months ago
- CiteME is a benchmark designed to test the abilities of language models in finding papers that are cited in scientific texts.☆48Updated 10 months ago
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- Evaluate uncertainty, calibration, accuracy, and fairness of LLMs on real-world survey data!☆24Updated 4 months ago
- ☆69Updated last year
- Official implementation of the ACL 2024: Scientific Inspiration Machines Optimized for Novelty☆85Updated last year
- ☆52Updated 3 months ago
- State-of-the-art paired encoder and decoder models (17M-1B params)☆44Updated 3 weeks ago
- PAIR.withgoogle.com and friend's work on interpretability methods☆200Updated last week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆207Updated this week
- ☆28Updated 6 months ago
- ☆22Updated 4 months ago
- SDLG is an efficient method to accurately estimate aleatoric semantic uncertainty in LLMs☆27Updated last year
- Flexible library for merging large language models (LLMs) via evolutionary optimization (ACL 2025 Demo).☆83Updated 3 weeks ago
- Sparse Autoencoder Training Library☆54Updated 4 months ago