Sparse autoencoders (SAEs) decompose language model activations into sparse features, but prompt transformations designed to preserve the underlying request can redistribute activity across them. A fe
2 comments
Representation Redistribution in Sparse Autoencoders was first seen on Hugging Face · Daily papers on Oct 28, 2026. Since then it appeared in 2 hourly checks across 1 day, peaking at #4 on Oct 28, 03:28 UTC. It is #4 on the list right now.
This page has little history so far; it is kept out of search results until the item has trended on at least two days.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
▲ as reported by Hugging Face.
Show that this trended, linking back to this page.
<a href="https://trendoday.com/hugging-face/papers/2610.21240-representation-redistribution-in-sparse-autoencoders"><img src="https://trendoday.com/badge/hugging-face/papers/2610.21240-representation-redistribution-in-sparse-autoencoders.svg" alt="Representation Redistribution in Sparse Autoencoders on TrendBoard" height="44"></a>
[](https://trendoday.com/hugging-face/papers/2610.21240-representation-redistribution-in-sparse-autoencoders)