English
Related papers

Related papers: Evaluating Adversarial Robustness of Concept Repre…

200 papers

Motivated by the hypothesis that neural network representations encode abstract, interpretable features as linearly accessible, approximately orthogonal directions, sparse autoencoders (SAEs) have become a popular tool in interpretability.…

Machine Learning · Computer Science 2025-11-05 Valérie Costa , Thomas Fel , Ekdeep Singh Lubana , Bahareh Tolooshams , Demba Ba

Transformer models have become state-of-the-art in decoding stimuli and behavior from neural activity, significantly advancing neuroscience research. Yet greater transparency in their decision-making processes would substantially enhance…

Quantitative Methods · Quantitative Biology 2025-06-18 Laurence Freeman , Philip Shamash , Vinam Arora , Caswell Barry , Tiago Branco , Eva Dyer

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

As large language models (LLMs) are increasingly deployed in real-world applications, the need to selectively remove unwanted knowledge while preserving model utility has become paramount. Recent work has explored sparse autoencoders (SAEs)…

Computation and Language · Computer Science 2026-04-28 Tomer Ashuach , Dana Arad , Aaron Mueller , Martin Tutek , Yonatan Belinkov

Sparse Autoencoders (SAEs) decompose large language model representations into interpretable features, but how these features interact under uncertainty remains poorly understood. We introduce Feature Rivalry -- negatively correlated SAE…

Machine Learning · Computer Science 2026-05-12 Harshavardhan

Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diffusion models.…

Machine Learning · Computer Science 2025-07-14 Stepan Shabalin , Ayush Panda , Dmitrii Kharlapenko , Abdur Raheem Ali , Yixiong Hao , Arthur Conmy

Steering vectors are a promising approach to control the behaviour of large language models. However, their underlying mechanisms remain poorly understood. While sparse autoencoders (SAEs) may offer a potential method to interpret steering…

Machine Learning · Computer Science 2024-11-14 Harry Mayne , Yushi Yang , Adam Mahdi

Large-scale pre-trained vision-language models like CLIP demonstrate remarkable zero-shot performance across diverse tasks. However, fine-tuning these models to improve downstream performance often degrades robustness against distribution…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Fabian Morelli , Arnas Uselis , Ankit Sonthalia , Seong Joon Oh

We present the first systematic study of Sparse Autoencoders (SAEs) on video representations. Standard SAEs decompose video into interpretable, monosemantic features but destroy temporal coherence: hard TopK selection produces unstable…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Atahan Dokme , Sriram Vishwanath

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

Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted attention due to…

Machine Learning · Computer Science 2026-05-13 Hyeonjin Kim , Hangyeol Jung , Heechan Yun , Sungjun Yun , Dong-Jun Han

Sparse Autoencoders (SAEs) have emerged as a promising solution for decomposing large language model representations into interpretable features. However, Paulo and Belrose (2025) have highlighted instability across different initialization…

Machine Learning · Computer Science 2025-06-24 Seonglae Cho , Harryn Oh , Donghyun Lee , Luis Eduardo Rodrigues Vieira , Andrew Bermingham , Ziad El Sayed

As large language models (LLMs) achieve strong performance on traditional benchmarks, there is an urgent need for more challenging evaluation frameworks that probe deeper aspects of semantic understanding. We introduce SAGE (Semantic…

Artificial Intelligence · Computer Science 2025-09-26 Samarth Goel , Reagan J. Lee , Kannan Ramchandran

Transformer architectures have been widely adopted for time series forecasting, yet whether the representational mechanisms that make them powerful in NLP actually engage on time series data remains unexplored. The persistent…

Machine Learning · Computer Science 2026-05-07 Alper Yıldırım

We introduce sparse autoencoder neural operators (SAE-NOs), a new class of sparse autoencoders that operate in function spaces rather than fixed-dimensional Euclidean representations. We formalize the functional representation hypothesis,…

Machine Learning · Computer Science 2026-05-11 Bahareh Tolooshams , Ailsa Shen , Anima Anandkumar

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

Although the semantic communications have exhibited satisfactory performance in a large number of tasks, the impact of semantic noise and the robustness of the systems have not been well investigated. Semantic noise is a particular kind of…

Signal Processing · Electrical Eng. & Systems 2022-05-24 Qiyu Hu , Guangyi Zhang , Zhijin Qin , Yunlong Cai , Guanding Yu , Geoffrey Ye Li

A central goal of interpretability is to recover representations of causally relevant concepts from the activations of neural networks. The quality of these concept representations is typically evaluated in isolation, and under implicit…

Machine Learning · Computer Science 2025-12-18 Aaron Mueller , Andrew Lee , Shruti Joshi , Ekdeep Singh Lubana , Dhanya Sridhar , Patrik Reizinger

A popular new method in mechanistic interpretability is to train high-dimensional sparse autoencoders (SAEs) on neuron activations and use SAE features as the atomic units of analysis. However, the body of evidence on whether SAE feature…

Machine Learning · Computer Science 2024-09-10 Maheep Chaudhary , Atticus Geiger

Interpretability can improve the safety, transparency and trust of AI models, which is especially important in healthcare applications where decisions often carry significant consequences. Mechanistic interpretability, particularly through…

‹ Prev 1 8 9 10 Next ›