Awesome-Interpretability-in-Large-Language-Models
This repository collects all relevant resources about interpretability in LLMs
- 415
- CC0-1.0
- 2 y ago
This repository collects all relevant resources about interpretability in LLMs
[ICML 2022] "Neural Implicit Dictionary via Mixture-of-Expert Training" by Peihao Wang, Zhiwen Fan, Tianlong Chen, Zhangyang Wang
This repository contains code for morphology-free analysis of functional fluorescence microscopy. The focal algorithm, Graph-Filtered Time-trace (GraFT) Dictionary Learning, is published in Charles et al. 2022 in the IEEE Transactions of Image Processing.
[ICLR 2026] AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features
Code for the blog post "Do block-sparse featurizers find concept manifolds in sentence embeddings?"