# InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders

arXiv: https://arxiv.org/abs/2412.12101 · HTML: https://mlsanity.com/paper/2412.12101/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- Placed in Interpreting biomedical and science models, one of 13 directions in Mechanistic interpretability.
- Builds on 9 of its 30 references that are in the map.
- First posted on arXiv 13 Nov 2024.

## Placed in

- Mechanistic interpretability / [Interpreting biomedical and science models](https://mlsanity.com/mechinterp/interpreting-biomedical-and-science-models/)

## Builds on (most cited first, 9 of 9)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Linear Algebraic Structure of Word Senses, with Applications to Polysemy](https://mlsanity.com/paper/1601.03764/) (2016)
- [ProGen2: Exploring the Boundaries of Protein Language Models](https://mlsanity.com/paper/2206.13517/) (2022)
- [Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors](https://mlsanity.com/paper/2103.15949/) (2021)
- [Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models](https://mlsanity.com/paper/2408.00113/) (2024)
- [NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals](https://mlsanity.com/paper/2407.14561/) (2024)
- [Insights Into the Inner Workings of Transformer Models for Protein Function Prediction](https://mlsanity.com/paper/2309.03631/) (2023)

## Built on by (most cited first, 30 of 66)

- [Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry](https://mlsanity.com/paper/2503.01822/) (2025)
- [Understanding the Repeat Curse in Large Language Models from a Feature Perspective](https://mlsanity.com/paper/2504.14218/) (2025)
- [Position: Use Sparse Autoencoders to Discover Unknowns](https://mlsanity.com/paper/2506.23845/) (2025)
- [Protein Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2502.17504/) (2025)
- [From superposition to sparse codes: interpretable representations in neural networks](https://mlsanity.com/paper/2503.01824/) (2025)
- [Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs](https://mlsanity.com/paper/2502.12352/) (2025)
- [Discovering and Steering Interpretable Concepts in Large Generative Music Models](https://mlsanity.com/paper/2505.18186/) (2025)
- [Towards Interpretable Protein Structure Prediction with Sparse Autoencoders](https://mlsanity.com/paper/2503.08764/) (2025)
- [Towards mechanistic understanding in a data-driven weather model: internal activations reveal interpretable physical features](https://mlsanity.com/paper/2512.24440/) (2025)
- [AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features](https://mlsanity.com/paper/2510.00404/) (2025)
- [AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders](https://mlsanity.com/paper/2602.05027/) (2026)
- [Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers](https://mlsanity.com/paper/2501.02393/) (2025)
- [Computational Protein Science in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2501.10282/) (2025)
- [ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning](https://mlsanity.com/paper/2506.07459/) (2025)
- [Controlling Repetition in Protein Language Models](https://mlsanity.com/paper/2602.00782/) (2026)
- [Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders](https://mlsanity.com/paper/2605.13930/) (2026)
- [Sparse Autoencoders for Low-N Protein Function Prediction and Design](https://mlsanity.com/paper/2508.18567/) (2025)
- [From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery](https://mlsanity.com/paper/2607.12474/) (2026)
- [Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders](https://mlsanity.com/paper/2508.09363/) (2025)
- [ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders](https://mlsanity.com/paper/2509.05309/) (2025)
- [A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima](https://mlsanity.com/paper/2512.05534/) (2025)
- [Protein Circuit Tracing via Cross-layer Transcoders](https://mlsanity.com/paper/2602.12026/) (2026)
- [Scaling Structure Aware Virtual Screening to Billions of Molecules with SPRINT](https://mlsanity.com/paper/2411.15418/) (2024)
- [Insights into a radiology-specialised multimodal large language model with sparse autoencoders](https://mlsanity.com/paper/2507.12950/) (2025)
- [Towards Understanding the Shape of Representations in Protein Language Models](https://mlsanity.com/paper/2509.24895/) (2025)
- [CXR-LanIC: Language-Grounded Interpretable Classifier for Chest X-Ray Diagnosis](https://mlsanity.com/paper/2510.21464/) (2025)
- [Discovering Interpretable Biological Concepts in Single-cell RNA-seq Foundation Models](https://mlsanity.com/paper/2510.25807/) (2025)
- [Unveiling Latent Knowledge in Chemistry Language Models through Sparse Autoencoders](https://mlsanity.com/paper/2512.08077/) (2025)
- [Circuits, Features, and Heuristics in Molecular Transformers](https://mlsanity.com/paper/2512.09757/) (2025)
- [Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks](https://mlsanity.com/paper/2602.06020/) (2026)

## Abstract (arXiv)

Protein language models (PLMs) have demonstrated remarkable success in protein modeling and design, yet their internal mechanisms for predicting structure and function remain poorly understood. Here we present a systematic approach to extract and analyze interpretable features from PLMs using sparse autoencoders (SAEs). By training SAEs on embeddings from the PLM ESM-2, we identify up to 2,548 human-interpretable latent features per layer that strongly correlate with up to 143 known biological concepts such as binding sites, structural motifs, and functional domains. In contrast, examining individual neurons in ESM-2 reveals up to 46 neurons per layer with clear conceptual alignment across 15 known concepts, suggesting that PLMs represent most concepts in superposition. Beyond capturing known annotations, we show that ESM-2 learns coherent concepts that do not map onto existing annotations and propose a pipeline using language models to automatically interpret novel latent features learned by the SAEs. As practical applications, we demonstrate how these latent features can fill in missing annotations in protein databases and enable targeted steering of protein sequence generation. Our results demonstrate that PLMs encode rich, interpretable representations of protein biology and we propose a systematic framework to extract and analyze these latent features. In the process, we recover both known biology and potentially new protein motifs. As community resources, we introduce InterPLM (interPLM.ai), an interactive visualization platform for exploring and analyzing learned PLM features, and release code for training and analysis at github.com/ElanaPearl/interPLM.