Layer-wise sparse autoencoder features from vision models are cosine-matched to voxel-level fMRI responses, creating a training-free voxel-to-feature dictionary for the ventral visual pathway.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
q-bio.NC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Sparse Autoencoders Bridge The Deep Learning Model and The Brain
Layer-wise sparse autoencoder features from vision models are cosine-matched to voxel-level fMRI responses, creating a training-free voxel-to-feature dictionary for the ventral visual pathway.