Interpreting Latent Protein Language Model Features with Geometric Annotations
q-bio.QM, cs.LG
Submitted: 2026-08-26
Updated: 2026-08-26
Code: https://github.com/siddharthsetlur/ProteinLens
Terminology
Sources
- Concept Bottleneck Language Models For protein design
- Toy Models of Superposition
- Automatically Interpreting Millions of Features in Large Language Models
- BERTology Meets Biology: Interpreting Attention in Protein Language Models
- The geometry of hidden representations of large transformer models
- Interpreting and Steering Protein Language Models through Sparse Autoencoders
- Towards Interpretable Protein Structure Prediction with Sparse Autoencoders
- ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders
- Scaling and evaluating sparse autoencoders
Related papers
- A likelihood-based framework for simultaneously learning both noise and growth dynamics using biologically-informed neural networks
- Automated Lesion Segmentation of Stroke MRI Using nnU-Net: A Comprehensive External Validation Across Acute and Chronic Lesions
- Resolving satellite-in situ mismatches in Net Primary Production using high-frequency in situ bio-optical observations in the subpolar Northwest Atlantic
- easyplater: The easy way to generate microplate designs deconvolved from multivariate clinical data
- Essential Workers at Risk: An Agent-Based Model (SAFE-ABM) with Bayesian Uncertainty Quantification
- OmniBioTwin: A System-of-Twinned-Systems Framework for Health Digital Twins