English
Related papers

Related papers: Automatically Interpreting Millions of Features in…

200 papers

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 interpretable…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Vladimir Zaigrajew , Hubert Baniecki , Przemyslaw Biecek

LLMs increasingly require surgical model editing to enhance domain-specific capabilities without incurring the computational cost or catastrophic forgetting associated with full fine-tuning. Sparse Autoencoders (SAEs) have emerged as a…

Machine Learning · Computer Science 2026-05-28 Li Lei , Madalina Ciobanu , Qingqing Mao , Ritankar Das

Interpretability is critical in high-stakes domains such as medical imaging, where understanding model decisions is essential for clinical adoption. In this work, we introduce Sparse Autoencoder (SAE)-based interpretability to breast…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Krishna Kanth Nakka

Despite strong performance in audio perception tasks, large audio-language models (AudioLLMs) remain opaque to interpretation. A major factor behind this lack of interpretability is that individual neurons in these models frequently…

Sound · Computer Science 2026-02-27 Townim Faisal Chowdhury , Ta Duc Huy , Siqi Pan , Jeremy Stoddard , Zhibin Liao

Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and weakly grounded features, while related…

Artificial Intelligence · Computer Science 2026-04-29 John Winnicki , Abeynaya Gnanasekaran , Eric Darve

Sparse autoencoders (SAEs) have emerged as a powerful tool for uncovering interpretable features in large language models (LLMs) through the sparse directions they learn. However, the sheer number of extracted directions makes comprehensive…

Computation and Language · Computer Science 2025-11-11 Xinyuan Yan , Shusen Liu , Kowshik Thopalli , Bei Wang

Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration to identify a canonical set of features is challenged by…

Machine Learning · Computer Science 2025-05-27 Xiangchen Song , Aashiq Muhamed , Yujia Zheng , Lingjing Kong , Zeyu Tang , Mona T. Diab , Virginia Smith , Kun Zhang

Sparse autoencoders (SAEs) have proven effective for extracting monosemantic features from large language models (LLMs), yet these features are typically identified in isolation. However, broad evidence suggests that LLMs capture the…

Artificial Intelligence · Computer Science 2026-02-13 Yifan Luo , Yang Zhan , Jiedong Jiang , Tianyang Liu , Mingrui Wu , Zhennan Zhou , Bin Dong

Recent interpretability work on large language models (LLMs) has been increasingly dominated by a feature-discovery approach with the help of proxy modules. Then, the quality of features learned by, e.g., sparse auto-encoders (SAEs), is…

Machine Learning · Computer Science 2025-10-28 Mengyu Ye , Jun Suzuki , Tatsuro Inaba , Tatsuki Kuribayashi

Sparse autoencoders (SAEs) are used to decompose neural network activations into sparsely activating features, but many SAE features are only interpretable at high activation strengths. To address this issue we propose to use binary sparse…

Machine Learning · Computer Science 2025-10-01 Lucia Quirke , Stepan Shabalin , Nora Belrose

Existing works are dedicated to untangling atomized numerical components (features) from the hidden states of Large Language Models (LLMs). However, they typically rely on autoencoders constrained by some training-time regularization on…

Machine Learning · Computer Science 2026-02-13 Hakaze Cho , Haolin Yang , Yanshu Li , Brian M. Kurkoski , Naoya Inoue

Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features. Typically, features learned by a single SAE are used for downstream applications. However, it has recently been shown that SAEs…

Machine Learning · Computer Science 2025-05-23 Soham Gadgil , Chris Lin , Su-In Lee

Sparse autoencoders (SAEs) model the activations of a neural network as linear combinations of sparsely occurring directions of variation (latents). The ability of SAEs to reconstruct activations follows scaling laws w.r.t. the number of…

Machine Learning · Computer Science 2025-09-05 Eric J. Michaud , Liv Gorton , Tom McGrath

In-context learning, the ability to adapt based on a few examples in the input prompt, is a ubiquitous feature of large language models (LLMs). However, as LLMs' in-context learning abilities continue to improve, understanding this…

Machine Learning · Computer Science 2024-10-03 Can Demircan , Tankred Saanum , Akshay K. Jagadish , Marcel Binz , Eric Schulz

Recent advances in Large Multimodal Models (LMMs) lead to significant breakthroughs in both academia and industry. One question that arises is how we, as humans, can understand their internal neural representations. This paper takes an…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Kaichen Zhang , Yifei Shen , Bo Li , Ziwei Liu

The cosine similarity between a large language model's hidden activations before and after Supervised Fine-Tuning (SFT) remains very high. This, at first glance, suggests that SFT leaves the model's activation geometry largely undisturbed.…

Artificial Intelligence · Computer Science 2026-05-13 Ruhaan Chopra

We investigate whether sparse autoencoders (SAEs) can be used to remove knowledge from language models. We use the biology subset of the Weapons of Mass Destruction Proxy dataset and test on the gemma-2b-it and gemma-2-2b-it language…

Machine Learning · Computer Science 2024-11-05 Eoin Farrell , Yeu-Tong Lau , Arthur Conmy

Modern LLMs face inference efficiency challenges due to their scale. To address this, many compression methods have been proposed, such as pruning and quantization. However, the effect of compression on a model's interpretability remains…

Machine Learning · Computer Science 2025-07-23 Suchit Gupte , Vishnu Kabir Chhabra , Mohammad Mahdi Khalili

Sparse autoencoders (SAEs) have emerged as a promising approach for learning interpretable features from neural network activations. However, the optimization landscape for SAE training can be challenging due to correlations in the input…

Machine Learning · Computer Science 2025-11-19 Ashwin Saraswatula , David Klindt

Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large…

Machine Learning · Computer Science 2026-05-19 Michał Brzozowski , Neo Christopher Chung