Pinned Loading

1. HypotheSAEs HypotheSAEs Public

   [ICML 2025] HypotheSAEs: Hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382

   Jupyter Notebook 68 21

2. wimhf wimhf Public

   What's In My Human Feedback? Explaining preferences in human feedback using interpretability + LLMs. https://arxiv.org/abs/2510.26202

   Python 2

3. LLM-publication-patterns-public LLM-publication-patterns-public Public

   [NAACL 2024] Topics, Authors, and Institutions in Large Language Model Research: Trends from 17K arXiv Papers https://arxiv.org/abs/2307.10700

   Jupyter Notebook 17

4. kundajelab/MPRA-DragoNN kundajelab/MPRA-DragoNN Public

   Code accompanying the paper "Deciphering regulatory DNA sequences and noncoding genetic variants using neural network models of massively parallel reporter assays"

   Python 12 5