English
Related papers

Related papers: Automatically Interpreting Millions of Features in…

200 papers

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their…

Information Retrieval · Computer Science 2026-02-18 Anton Klenitskiy , Konstantin Polev , Daria Denisova , Alexey Vasilev , Dmitry Simakov , Gleb Gusev

Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse autoencoders (SAEs) make hidden activations more interpretable by exposing latent features that often…

Sparse Autoencoders (SAEs) are widely used to steer large language models (LLMs), based on the assumption that their interpretable features naturally enable effective model behavior steering. Yet, a fundamental question remains unanswered:…

Machine Learning · Computer Science 2025-10-07 Xu Wang , Yan Hu , Benyou Wang , Difan Zou

There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). However, current methods face fundamental challenges in…

Computation and Language · Computer Science 2025-12-02 Ruben Härle , Felix Friedrich , Manuel Brack , Stephan Wäldchen , Björn Deiseroth , Patrick Schramowski , Kristian Kersting

Sparse autoencoders (SAEs) improve interpretability in multimodal models, but it remains unclear whether SAE features form modular, composable units for reasoning-an assumption underlying many intervention-based steering methods. We test…

Artificial Intelligence · Computer Science 2026-03-27 Yunpeng Zhou

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…

Machine Learning · Computer Science 2026-01-30 Yuhang Liu , Erdun Gao , Dong Gong , Anton van den Hengel , Javen Qinfeng Shi

Sparse autoencoders (SAEs) are widely used in mechanistic interpretability research for large language models; however, the state-of-the-art method of using $k$-sparse autoencoders lacks a theoretical grounding for selecting the…

Machine Learning · Computer Science 2025-08-11 Sewoong Lee , Adam Davies , Marc E. Canby , Julia Hockenmaier

Deterministically controlling the target generation language of large multilingual language models (LLMs) remains a fundamental challenge, particularly in zero-shot settings where neither explicit language prompts nor fine-tuning are…

Computation and Language · Computer Science 2025-10-17 Cheng-Ting Chou , George Liu , Jessica Sun , Cole Blondin , Kevin Zhu , Vasu Sharma , Sean O'Brien

We identify semantically coherent, context-consistent network components in large language models (LLMs) using coactivation of sparse autoencoder (SAE) features collected from just a handful of prompts. Focusing on concept-relation…

Computation and Language · Computer Science 2026-04-21 Ruixuan Deng , Xiaoyang Hu , Miles Gilberti , Shane Storks , Aman Taxali , Mike Angstadt , Chandra Sripada , Joyce Chai

Despite rapid adoption and deployment of large language models (LLMs), the internal computations of these models remain opaque and poorly understood. In this work, we seek to understand how high-level human-interpretable features are…

Machine Learning · Computer Science 2023-06-06 Wes Gurnee , Neel Nanda , Matthew Pauly , Katherine Harvey , Dmitrii Troitskii , Dimitris Bertsimas

Sparse auto-encoders (SAEs) have become a prevalent tool for interpreting language models' inner workings. However, it is unknown how tightly SAE features correspond to computationally important directions in the model. This work…

Machine Learning · Computer Science 2025-02-25 Thomas Dooms , Daniel Wilhelm

Sparse autoencoders (SAEs) are now standard tools for decomposing language model activations into interpretable features, and automated interpretability pipelines routinely assign each feature a short natural-language explanation. Existing…

Machine Learning · Computer Science 2026-05-14 Jordan F. McCann

Protein language models have revolutionized structure prediction, but their nonlinear nature obscures how sequence representations inform structure prediction. While sparse autoencoders (SAEs) offer a path to interpretability here by…

Biomolecules · Quantitative Biology 2025-03-13 Nithin Parsan , David J. Yang , John J. Yang

Sparse Autoencoders (SAEs) have shown to find interpretable features in neural networks from polysemantic neurons caused by superposition. Previous work has shown SAEs are an effective tool to extract interpretable features from the early…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Matthew Bozoukov

With the integration of image modality, the semantic space of multimodal large language models (MLLMs) is more complex than text-only models, making their interpretability more challenging and their alignment less stable, particularly…

Machine Learning · Computer Science 2025-06-18 Hantao Lou , Changye Li , Jiaming Ji , Yaodong Yang

Sparse autoencoders (SAEs) offer a natural path toward comparable explanations across different representation spaces. However, current SAEs are trained per modality, producing dictionaries whose features are not directly understandable and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Difei Gu , Yunhe Gao , Gerasimos Chatzoudis , Zihan Dong , Guoning Zhang , Bangwei Guo , Yang Zhou , Mu Zhou , Dimitris Metaxas

We describe HypotheSAEs, a general method to hypothesize interpretable relationships between text data (e.g., headlines) and a target variable (e.g., clicks). HypotheSAEs has three steps: (1) train a sparse autoencoder on text embeddings to…

Computation and Language · Computer Science 2025-06-10 Rajiv Movva , Kenny Peng , Nikhil Garg , Jon Kleinberg , Emma Pierson

Sparse autoencoders (SAEs) are widely used for interpreting language model activations. A key evaluation metric is the increase in cross-entropy loss between the original model logits and the reconstructed model logits when replacing model…

Machine Learning · Computer Science 2025-04-01 Adam Karvonen

Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models. One key issue with SAEs is their inability to directly model multidimensional features.…

Machine Learning · Computer Science 2026-05-12 Collin Francel

Altruism is fundamental to human societies, fostering cooperation and social cohesion. Recent studies suggest that large language models (LLMs) can display human-like prosocial behavior, but the internal computations that produce such…

General Economics · Economics 2026-04-22 Shuhuai Zhang , Shu Wang , Zijun Yao , Chuanhao Li , Xiaozhi Wang , Songfa Zhong , Tracy Xiao Liu