Related papers: InterPLM: Discovering Interpretable Features in Pr…

What latent features are encoded in language model (LM) representations? Recent work on training sparse autoencoders (SAEs) to disentangle interpretable features in LM representations has shown significant promise. However, evaluating the…

Proteins adopt multiple structural conformations to perform their diverse biological functions, and understanding these conformations is crucial for advancing drug discovery. Traditional physics-based simulation methods often struggle with…

With the exponential increase of the protein sequence databases over time, multiple-sequence alignment (MSA) methods, like PSI-BLAST, perform exhaustive and time-consuming database search to retrieve evolutionary information. The resulting…

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…

Automated interpretability research aims to identify concepts encoded in neural network features to enhance human understanding of model behavior. Within the context of large language models (LLMs) for natural language processing (NLP),…

A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make fine-grained circuit analysis on transformer-based language…

We propose ProtLLM, a versatile cross-modal large language model (LLM) for both protein-centric and protein-language tasks. ProtLLM features a unique dynamic protein mounting mechanism, enabling it to handle complex inputs where the natural…

Protein language models leverage evolutionary information to perform state-of-the-art 3D structure and zero-shot variant prediction. Yet, extracting and explaining all the mutational interactions that govern model predictions remains…

Sparse autoencoders (SAEs) have become an important tool for analyzing and interpreting the activation space of transformer-based language models (LMs). However, SAEs suffer several shortcomings that diminish their utility and internal…

This paper demonstrates that language models are strong structure-based protein designers. We present LM-Design, a generic approach to reprogramming sequence-based protein language models (pLMs), that have learned massive sequential…

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

We introduce Concept Bottleneck Protein Language Models (CB-pLM), a generative masked language model with a layer where each neuron corresponds to an interpretable concept. Our architecture offers three key benefits: i) Control: We can…

Deciphering the function of unseen protein sequences is a fundamental challenge with broad scientific impact, yet most existing methods depend on task-specific adapters or large-scale supervised fine-tuning. We introduce the…

Proteins, as essential biomolecules, play a central role in biological processes, including metabolic reactions and DNA replication. Accurate prediction of their properties and functions is crucial in biological applications. Recent…

Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene on model behavior.…

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…

Developing human understandable interpretation of large language models (LLMs) becomes increasingly critical for their deployment in essential domains. Mechanistic interpretability seeks to mitigate the issues through extracts…

Protein language models (PLMs) learn contextual representations from protein sequences and are profoundly impacting various scientific disciplines spanning protein design, drug discovery, and structural predictions. One particular research…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing but also pose significant privacy risks by memorizing and leaking Personally Identifiable Information (PII). Existing mitigation…

Sparse autoencoders (SAEs) are a popular method for interpreting concepts represented in large language model (LLM) activations. However, there is a lack of evidence regarding the validity of their interpretations due to the lack of a…