On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders
Elana Simon,
·
2026-06-01
·
via cs.LG updates on arXiv.org
arXiv:2605.31518v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) decompose neural network activatio…
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。