NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
172 results for “keyword:"sparse autoencoders"” in ICLR 2027. 33 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]PACO-SAE: Evaluating Concept Grounding and Feature Splitting in Vision Sparse Autoencoders▼4.5k2.67
[PDF]Weight-Dictionary Decomposition: Reading a Transformer's Residual Stream with Its Own Writes▼1361.33
[PDF]Don't Mind the Gap: Interpretable Vision-Language Models via Independent Sparse Autoencoders▲3.0k2.33
[PDF]H-MSAE: Hierarchical Sparse Concept Coverage for Efficient and Diverse Instruction Data Selection▲5.4k3.00
[PDF]InvExplain: An Agentic Interpretation Framework for SAE Features via Training-Free Diffusion Inversion▼5.8k2.33
[PDF]Frequency, Direction, and Feature Sharing: Dissecting Co-activation in Sparse Autoencoders▲13k2.33
[PDF]Ambient Dimension Governs Whether Frozen Single-Cell Embeddings Can Be Edited and Interpreted▼1.2k1.67
Withdrawn or desk rejected (33)
[PDF]SN-ABSTOPK: AN UNROLLED SPATIAL-NORMATIVE SPARSE AUTOENCODER FOR MEDICAL FOUNDATION MODELSWithdrawn1.00