Inserting a TopK sparse autoencoder into the POYO+ neural decoder preserves performance while yielding latent units selective for orientation, temporal frequency, and genetic background, and ablating them causally impairs the corresponding decoding.
and Bengio, Y .Understanding intermediate layers using linear classifier probes.2017
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
q-bio.QM 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Beyond Black Boxes: Enhancing Interpretability of Transformers Trained on Neural Data
Inserting a TopK sparse autoencoder into the POYO+ neural decoder preserves performance while yielding latent units selective for orientation, temporal frequency, and genetic background, and ablating them causally impairs the corresponding decoding.