Sparse autoencoder interpretability of InstaNovo

adjacent · Sparse autoencoder

Sparse autoencoder interpretability of InstaNovo: adjacent · Sparse autoencoder. Mechanistic-interpretability probe of a de novo sequencer: sparse autoencoders trained on the internal activations at four depths of InstaNovo’s spectrum encoder…

Mechanistic-interpretability probe of a de novo sequencer: sparse autoencoders trained on the internal activations at four depths of InstaNovo’s spectrum encoder, paired with a fragment-ion annotation pipeline that labels every peak with chemical concepts derived from first principles, so learned features can be matched to chemical events. Reconstructs the encoder’s representations at over 92% fidelity per layer while preserving more than 99.5% of sequencing loss, and finds the feature-to-concept associations are organised by depth: physical spectral properties sharpest in early layers, cleavage specificity and modification localisation emerging deeper. Causal ablation tests how far those associations reflect genuine use by the model, and exposes a structural limit in correlation-based feature ranking when chemical concepts co-occur.

Kind adjacent
Family Sparse autoencoder
Deep learning yes
Acquisition DDA

Papers

Authors (1)

Mohammed Esameldin Adam Nagi

Seen in the charts

Back to the full map

Back to top