Generative Latent Priors for Interpreting and Steering Protein Language Models
cs.AI, cs.LG
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Automated Neuron Labelling Enables Generative Steering and Interpretability in Protein Language Models
- A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
- Decomposing The Dark Matter of Sparse Autoencoders
- Steering Protein Language Models
- Scaling Laws for Neural Language Models
- Learning a Generative Meta-Model of LLM Activations
- How to make the most of your masked language model for protein engineering
- Sparse Autoencoders Trained on the Same Data Learn Different Features
- Steering Language Models With Activation Engineering
- Interpreting and Steering Protein Language Models through Sparse Autoencoders
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents