This work introduces an automated and scalable method for interpreting SAE features in ESM-2 by using geometrically inspired features of the protein $\text{C}_\alpha$ backbone, providing a robust method of annotating proteins activated within SAE neurons at a residue level, providing a bridge between mechanistic interpretability and structural biology.
Abstract
Protein language models (pLMs) encode information about protein sequences which enable downstream tasks such as structure prediction, but their internal representations are not well understood. Sparse autoencoders (SAEs) provide a promising tool to disentangle latent pLM representations into interpretable features, but existing annotation pipelines largely rely on protein-level annotations derived from database labels and LLM annotations of top activating sequences. Such annotations can overlook the localized residue-level and geometric patterns encoded by sparse features. We introduce an automated and scalable method for interpreting SAE features in ESM-2 by using geometrically inspired features of the protein $\text{C}_\alpha$ backbone. Across ESM-2 8M layers, an FDR-controlled discovery analysis shows that local geometry is significantly associated with many SAE features, with varying levels of predictive strength, expanding coverage beyond database and sequence-based methods. In particular, geometry can distinguish SAE features sharing the same database annotation, revealing substructure within known biological labels. A significant portion of SAE features activate on unannotated metagenomic protein sequences enabling us to use our SAE annotations to better understand these sequences. In addition, ablation experiments at the level of contact prediction show that removing found geometric features shifts ESM-2's predicted contact maps in the direction of the descriptor. This provides a robust method of annotating proteins activated within SAE neurons at a residue level, providing a bridge between mechanistic interpretability and structural biology.
Applications to thioredoxins, visual opsins, and Tara Oceans environmental diatom cold-shock proteins show that PLMView can move from interpretable residue-level determinants in well-studied protein families to large-scale environmental functional discovery, linking molecular specialization to ecological distribution and transcriptional deployment across the global ocean.
Motivation RNA language models learn representations that support structure and function prediction, but which biological concepts their hidden states encode remains unclear. Sparse autoencoders (SAEs) decompose hidden states into interpretable features, yet have not been applied to RNA language models, where byte-pair tokenization breaks the one-token-one-nucleotide correspondence that nucleotide-level attribution assumes. Results We present SPIRAL, a layer-wise SAE analysis of BiRNA-BERT. Independent SAEs at layers 0, 5, and 11 expand each 768-dimensional hidden state into 6,144 features while preserving model behaviour (explained variance above 0.99997; masked-language-model sequence recovery near 99.7%). Tokenizer-aware offset propagation aligns features to nucleotides: at layer 5, 44.3% of tested features are significantly associated with bpRNA secondary-structure classes (mean enrichment 1.61 ×), and all 1,237 eligible features with RNAcentral RNA types. Sparse profiles raise k-nearest-neighbour balanced accuracy from 0.328 to 0.359 over dense embeddings at layer 5. Availability and Implementation Source code is available at https://github.com/SadatHossain01/SPIRAL; the code, evaluation data, and trained SAE checkpoints are archived at https://doi.org/10.5281/zenodo.21891845. Contact mrahman@cse.buet.ac.bd Supplementary information Supplementary data are presented alongside the manuscript.
M. Hossain, MD. Roqunuzzaman Sojib, Md Toki Tahmid et al.· bioRxiv· 0 citations
A high-resolution layer-by-layer interpretability analysis of 8 models from the ESM2 and AMPLIFY families on 22 concepts from human proteome annotations found that these models encode concepts of increasing levels of complexity along their depth: basic physicochemical properties and linear motifs are best captured by early-layer embeddings, secondary structure from subsequent layers, and domain-level semantics from middle layers.
Shawn T. Whitfield, Tom Marty, Robert M. Vernon et al.· bioRxiv· 0 citations
Over eight diverse protein foundational models trained on 550,120 SwissProt proteins with AlphaFold structures, enriched embeddings improved zero-shot remote homology retrieval, increasing Precision@10 and MRR by up to 0.13 and 0.11, respectively.
Gabriel Bianchin de Oliveira, Fahad Saeed· bioRxiv· 0 citations
Protein language models (PLMs) have transferred the latest advances from natural language processing to computational biology. These models, trained on large corpora of protein sequence data, are widely used to translate amino acid sequences into latent-space embeddings, ready for use in diverse downstream tasks (DTs). By consensus, embeddings from the models'last layers are used, while the models'internal behavior remains poorly understood. We analyzed 13 PLMs across 15 DTs and 9 datasets to assess the value of embeddings from intermediate PLM layers. We trained probe models on embeddings from each layer, compared their performance, and showed that the last layers of PLMs rarely produced embeddings that led to the best results on downstream tasks. Furthermore, we identified a connection between how models learn a certain DT and the similarity between that DT and the pre-training objective. For example, for residue-level downstream tasks, we observed a steady increase in performance across almost all PLM layers, which we attributed to their similarity to most PLMs'pre-training objectives. To allow the community to capitalize on our findings, we provide PLMSommelier, a Python package that automatically identifies the best PLM layer for a given DT with ~98% accuracy and creates a truncated model using only the early layers up to the best-performing layer. This will help users save time and memory during inference and yield better predictive performance.
R. Joeres, Ilya S. Senatorov, A. Kolchina et al.· 0 citations
A modular Context-Augmented Prompting framework that enables agentic tool use at inference time: a trained GNN expert model provides a predictive hint with confidence, and a GNN extracts an instance-specific explanatory subgraph via a necessity-based edge-drop intervention.
K. Bougiatiotis, Dimitrios Kelesis, Georgios Paliouras· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
