paper-with-me

Papers

SAE-RNA: A Sparse Autoencoder Model for Interpreting RNA Language Model Representations

2025-10-03 · Taehan Kim, Sangdae Nam arxiv

Deep learning, particularly with the advancement of Large Language Models, has transformed biomolecular modeling, with protein language models such as ESM inspiring emerging RNA language models such as RiNALMo. Recent work has begun applying sparse autoencoders (SAEs) to protein language model representations, exploring representation-level interpretability in biomolecular models. Here, we explore whether SAEs can provide interpretable feature decompositions of RNA language model representations, while also examining their limitations in this setting. We present SAE-RNA, interpretability model that analyzes RiNALMo representations and maps them to known human-level biological features. Rather than claiming definitive biological concept discovery, our study frames SAE-based analysis as a representation-level probe for characterizing how RNA language models organize biological information internally. More broadly, SAE-RNA provides a feature-level framework for comparing RNA groups and identifying sparse representation components associated with RNA family identity or structural context.

📄 PDF Abstract BibTeX arXiv:2510.02734

Code (0)

등록된 구현이 없습니다.

Tasks

Protein Language Model

Similar Papers 제목 키워드 기반

Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders

2025-05-12 · Dong Shu, Xuansheng Wu, Haiyan Zhao, Mengnan Du 외

Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional approaches to analyzing SAEs typically …

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

2025-03-24 · Andrey Galichin, Alexey Dontsov, Polina Druzhinina, Anton Razzhigaev 외

Large Language Models (LLMs) have achieved remarkable success in natural language processing. Recent advances have led to the developing of a new class of reasoning LLMs; for example, open-source DeepSeek-R1 has achieved…

All

Interpreting CLIP with Hierarchical Sparse Autoencoders

2025-02-27 · Vladimir Zaigrajew, Hubert Baniecki, Przemyslaw Biecek

Sparse autoencoders (SAEs) are useful for detecting and steering interpretable features in neural networks, with particular potential for understanding complex multimodal representations. Given their ability to uncover i…

Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders

2026-06-08 · Nikita Koriagin, Georgii Aparin, Nikita Balagansky, Daniil Gavrilov arxiv

Language models increasingly serve as the backbone of text-to-speech (TTS) systems, yet we understand little about the representations they build when text and generated speech tokens share a single residual stream. We t…

Interpreting and Steering Protein Language Models through Sparse Autoencoders

2025-02-13 · Edith Natalia Villegas Garcia, Alessio Ansuini

The rapid advancements in transformer-based language models have revolutionized natural language processing, yet understanding the internal mechanisms of these models remains a significant challenge. This paper explores …