A cross-attention SAE with sparsemax attention achieves lower reconstruction loss and higher-quality concepts than fixed-sparsity baselines by making activation counts data-dependent.
Enhancing neural network interpretability with feature-aligned sparse autoencoders
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Sparse autoencoders enable phase synchronization in frozen graph CFD surrogates through Hilbert-identified oscillatory features and SVD-based time-varying rotations.
citing papers explorer
-
Improving Sparse Autoencoder with Dynamic Attention
A cross-attention SAE with sparsemax attention achieves lower reconstruction loss and higher-quality concepts than fixed-sparsity baselines by making activation counts data-dependent.
-
Sparse Autoencoders as a Steering Basis for Phase Synchronization in Graph-Based CFD Surrogates
Sparse autoencoders enable phase synchronization in frozen graph CFD surrogates through Hilbert-identified oscillatory features and SVD-based time-varying rotations.