Amplifying specific sparse-autoencoder latents inside ESM-2 biases sequence generation toward zinc finger motifs, with a low success rate and incomplete statistical validation.
Simulating 500 million years of evolution with a language model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Interpreting and Steering Protein Language Models through Sparse Autoencoders
Amplifying specific sparse-autoencoder latents inside ESM-2 biases sequence generation toward zinc finger motifs, with a low success rate and incomplete statistical validation.