SoccerDream AI ← AI 圈资讯 论文研究

Separating Interpretability and Reconstruction in Sparse Autoencoders

arXiv 机器学习 ·

arXiv:2611.25165v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) are effective tools for mechanistic interpretability by decomposing neural representations into sparse and interpretable features. However, a single sparse representation in traditional SAEs is responsible for both reconstruction fidelity and interpretability, which are not guaranteed to align. To separate these objectives, we propose DualSAE, a modular framework that augments standard SAEs with a plug-in Residual Branch. A standard SAE serves as the Sparse Branch, learning a sparse code that contains the dominant seman

阅读原文 · arXiv 机器学习
本文由 SoccerDream AI 自动聚合索引,内容版权归原作者与 arXiv 机器学习 所有。
本站仅作技术动态聚合,不构成任何形式的建议。
AI 生成内容标识:本页的分析结论与文字内容由 SoccerDream AI 大语言模型自动生成,依据《人工智能生成合成内容标识办法》予以标注;赛事数据、赛果与市场指数来自公开数据源,并经系统规则校验。内容仅供研究参考,不构成任何建议。