arXiv:2512. 07355v2 Announce Type: replace Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge.
By Alexandre Rocchi, Thomas Fel, Gianni Franchi
arXiv:2607. 08605v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept.
By Weiduo Liao, Yunqiao Yang, Ying Wei
arXiv:2606. 31699v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated features can serve as controllable intervention points.
By Enrico Cassano, Riccardo Renzulli, Rayyan Ahmed, Marco Grangetto, Stephan Alaniz
arXiv:2606. 16193v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representations remain difficult to interpret.
By Yusong Zhao, Hengyi Wang, Tanuja Ganu, Akshay Nambi, Hao Wang
arXiv:2606. 24716v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely rely on proxy metrics or qualitative inspection rather than measuring semantic correspondence.
By Jonas Klotz, Cassio F. Dantas, Pallavi Jain, Diego Marcos, Beg\"um Demir
The paper introduces Dynamic Semantic Steering (DSS), a training‑free, inference‑time defense for robust concept erasure in text‑to‑image diffusion models. DSS models local semantic neighborhoods geometrically, automatically identifies benign semantic anchors, and applies context‑aware, constrained feature correction using cross‑attention signals. Experiments show DSS achieves an average erasure rate of 91.0%, outperforming prior defenses while reducing semantic drift and preserving generation fidelity.
By Qinghui Gong, Zhengchun Zhou, Hua Meng, Yihuai Liang, Yuxuan Zhang