Transcoders Beat Sparse Autoencoders for Interpretability
arxiv.org ↗(2025) - shows transcoders (reconstructing layer outputs from inputs) yield more interpretable features than SAEs; introduces skip transcoders.
AboutVisit arxiv.org ↗
(2025) - shows transcoders (reconstructing layer outputs from inputs) yield more interpretable features than SAEs; introduces skip transcoders.
This entry links to an external website rather than a GitHub repository, so there's no README to display here.