unembedding

Here is 1 public repository matching this topic...

hematteo / sparse-readout-prism

Companion code for the paper "Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens" (arXiv:2609.01936). Pretrained dictionaries: hf.co/hematteo/sparse-readout-prism

language-models sparse-autoencoders interpretability mechanistic-interpretability logit-lens unembedding

Updated Sep 3, 2026
Python

Add this topic to your repo

To associate your repository with the unembedding topic, visit your repo's landing page and select "manage topics."

Learn more