arXiv:2608. 12010v1 Announce Type: new Abstract: Equivariant Neural Networks (ENNs) have empowered numerous applications in scientific fields.
By Ning Lin, Jiacheng Cen, Anyi Li, Wenbing Huang, Hao Sun
Equivariant Neural Networks (ENNs) have empowered numerous applications in scientific fields. Despite their remarkable capacity for representing geometric structures, ENNs suffer from degraded expressivity when processing symmetric inputs: the output representations are invariant to transformations that extend beyond the input's symmetries.
The paper investigates Sparse Autoencoders (SAEs) by applying dictionary learning identifiability results to derive constraints on optimal dictionary learning features. It shows that optimal features cannot activate simultaneously, explaining SAE oddities such as hierarchical splitting, absorption, dense antipodal features, and infinite feature splitting as consequences of the dictionary learning objective. The derived constraints also serve as diagnostics, revealing that real SAEs perform well on training data but fail on increasingly distant test data.
By William Dorrell
arXiv:2606. 18383v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable features from language models (LMs), yet a central question remains: when can an SAE-based explanation be treated as a faithful view of an underlying frozen LM We study this through a post-hoc generalization framework that certifies the LM via a sparse proxy, obtained by replacing a native hidden activation with its pretrained SAE reconstruction.
By Dibyanayan Bandyopadhyay, Asif Ekbal
arXiv:2606. 12138v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are widely used to interpret neural network representations, but their utility depends on whether the learned features are reproducible across training runs.
By Gleb Gerasimov, Timofei Rusalev, Nikita Balagansky, Daniil Laptev, Vadim Kurochkin, Daniil Gavrilov
arXiv:2604. 00208v2 Announce Type: replace Abstract: Comparing internal representations is a central goal in neuroscience and machine learning, but standard linear alignment metrics (Representational Similarity Analysis, Centered Kernel Alignment, and linear regression) are frequently applied to neural activity coordinates rather than on the underlying features.
By Sunny Liu, Habon Issa, Andr\'e Longon, Liv Gorton, Meenakshi Khosla, Alex Williams, David Klindt