English
Related papers

Related papers: I Have Covered All the Bases Here: Interpreting Re…

200 papers

Sparse Autoencoder (SAE) features have become essential tools for mechanistic interpretability research. SAE features are typically characterized by examining their activating examples, which are often "monosemantic" and align with human…

Artificial Intelligence · Computer Science 2025-09-30 Claire Tian , Katherine Tian , Nathan Hu

Sparse autoencoders (SAEs) have emerged as a powerful technique for decomposing language model representations into interpretable features. Current interpretation methods infer feature semantics from activation patterns, but overlook that…

Machine Learning · Computer Science 2026-02-02 Yiting Liu , Zhi-Hong Deng

Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features activate, not which change model outputs when amplified. We introduce Control Reinforcement…

Machine Learning · Computer Science 2026-05-05 Seonglae Cho , Zekun Wu , Adriano Koshiyama

Sparse autoencoders (SAEs) are a popular tool for interpreting large language model activations, but their utility in addressing open questions in interpretability remains unclear. In this work, we demonstrate their effectiveness by using…

Machine Learning · Computer Science 2025-04-21 Dmitrii Kharlapenko , Stepan Shabalin , Fazl Barez , Arthur Conmy , Neel Nanda

As Large Language Models become integral to software development, with substantial portions of AI-suggested code entering production, understanding their internal correctness mechanisms becomes critical for safe deployment. We apply sparse…

Software Engineering · Computer Science 2025-10-06 Kriz Tahimic , Charibeth Cheng

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

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

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

Large Language Models (LLMs) offer extensive knowledge across various domains, but they may inadvertently memorize sensitive, unauthorized, or malicious data, such as personal information in the medical and financial sectors. Machine…

Computation and Language · Computer Science 2024-10-16 YuXuan Wu , Bonaventure F. P. Dossou , Dianbo Liu

Identifying the features learned by neural networks is a core challenge in mechanistic interpretability. Sparse autoencoders (SAEs), which learn a sparse, overcomplete dictionary that reconstructs a network's internal activations, have been…

Machine Learning · Computer Science 2024-05-27 Dan Braun , Jordan Taylor , Nicholas Goldowsky-Dill , Lee Sharkey

Large language models (LLMs) can store a significant amount of factual knowledge in their parameters. However, their parametric knowledge may conflict with the information provided in the context -- this phenomenon, known as…

Computation and Language · Computer Science 2025-02-11 Yu Zhao , Alessio Devoto , Giwon Hong , Xiaotang Du , Aryo Pradipta Gema , Hongru Wang , Xuanli He , Kam-Fai Wong , Pasquale Minervini

Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We propose a continuous…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Leander Girrbach , Zeynep Akata

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting language model activations by decomposing them into sparse, interpretable features. A popular approach is the TopK SAE, that uses a fixed number of the most active…

Machine Learning · Computer Science 2024-12-10 Bart Bussmann , Patrick Leask , Neel Nanda

Sparse autoencoders (SAEs) are widely used in mechanistic interpretability to project LLM activations onto sparse latent spaces. However, sparsity alone is an imperfect proxy for interpretability, and current training objectives often…

Machine Learning · Computer Science 2026-04-09 Vivek Narayanaswamy , Kowshik Thopalli , Bhavya Kailkhura , Wesam Sakla

Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult. Representation-level steering addresses this by adding language-specific vectors to model…

Computation and Language · Computer Science 2026-04-07 Sing Hieng Wong , Hassan Sajjad , A. B. Siddique

While sparse autoencoders (SAEs) successfully extract interpretable features from language models, applying them to audio generation faces unique challenges: audio's dense nature requires compression that obscures semantic meaning, and…

Machine Learning · Computer Science 2025-10-31 Nathan Paek , Yongyi Zang , Qihui Yang , Randal Leistikow

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting neural networks by extracting the concepts represented in their activations. However, choosing the size of the SAE dictionary (i.e. number of learned concepts)…

Machine Learning · Computer Science 2025-03-25 Bart Bussmann , Noa Nabeshima , Adam Karvonen , Neel Nanda

Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoencoders (SAEs) are widely used for interpretability, their robustness implications remain…

Machine Learning · Computer Science 2026-04-22 Ahson Saiyed , Sabrina Sadiekh , Chirag Agarwal

Sparse Autoencoders (SAEs) are a powerful dictionary learning technique for decomposing neural network activations, translating the hidden state into human ideas with high semantic value despite no external intervention or guidance.…

Machine Learning · Computer Science 2025-12-17 Albert Miao , Chenliang Zhou , Jiawei Zhou , Cengiz Oztireli

Audio pretrained models are widely employed to solve various tasks in speech processing, sound event detection, or music information retrieval. However, the representations learned by these models are unclear, and their analysis mainly…