English
Related papers

Related papers: Mechanistic Permutability: Match Features Across L…

200 papers

Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse,…

Machine Learning · Computer Science 2024-06-26 Connor Kissane , Robert Krzyzanowski , Joseph Isaac Bloom , Arthur Conmy , Neel Nanda

Sparse Autoencoders (SAEs) have emerged as a predominant tool in mechanistic interpretability, aiming to identify interpretable monosemantic features. However, how does sparse encoding organize the representations of activation vector from…

Machine Learning · Computer Science 2025-05-29 Wenjie Sun , Bingzhe Wu , Zhile Yang , Chengke Wu

Intermediate layers of large language models (LLMs) best predict human brain responses to language, one of the most robust findings in computational neurolinguistics, yet why remains mechanistically unexplained. We address this gap by…

Computation and Language · Computer Science 2026-05-25 Dongxin Guo , Jikun Wu , Siu Ming Yiu

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 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…

We introduce a new approach to systematically map features discovered by sparse autoencoder across consecutive layers of large language models, extending earlier work that examined inter-layer feature links. By using a data-free cosine…

Machine Learning · Computer Science 2025-07-28 Daniil Laptev , Nikita Balagansky , Yaroslav Aksenov , Daniil Gavrilov

Sparse Autoencoders (SAEs) have emerged as a promising tool for interpreting neural networks by decomposing their activations into sparse sets of human-interpretable features. Recent work has introduced multiple SAE variants and…

Machine Learning · Computer Science 2026-02-17 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Rogov , Ivan Oseledets , Elena Tutubalina

A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early work focused on individual neurons, evidence that neurons…

Computation and Language · Computer Science 2026-05-05 Or Shafran , Atticus Geiger , Mor Geva

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

Understanding the internal machinations of deep Transformer-based NLP models is more crucial than ever as these models see widespread use in various domains that affect the public at large, such as industry, academia, finance, health. While…

Computation and Language · Computer Science 2026-05-13 Dan Pluth , Zachary Nicholas Houghton , Yu Zhou , Vijay K. Gurbani

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

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

Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for…

Machine Learning · Computer Science 2026-04-17 Dongsheng Wang , Jinsen Zhang , Dawei Su , Hui Huang

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

Fine-tuning pre-trained transformers is a powerful technique for enhancing the performance of base models on specific tasks. From early applications in models like BERT to fine-tuning Large Language Models (LLMs), this approach has been…

Computation and Language · Computer Science 2025-02-25 Suneel Nadipalli

A key challenge in interpretability is to decompose model activations into meaningful features. Sparse autoencoders (SAEs) have emerged as a promising tool for this task. However, a central problem in evaluating the quality of SAEs is the…

Machine Learning · Computer Science 2024-10-11 Constantin Venhoff , Anisoara Calinescu , Philip Torr , Christian Schroeder de Witt

Sparse Autoencoders (SAEs) have been proposed as an unsupervised approach to learn a decomposition of a model's latent space. This enables useful applications such as steering - influencing the output of a model towards a desired concept -…

Machine Learning · Computer Science 2025-12-23 Dana Arad , Aaron Mueller , Yonatan Belinkov

Recent work by Anthropic on Mechanistic interpretability claims to understand and control Large Language Models by extracting human-interpretable features from their neural activation patterns using sparse autoencoders (SAEs). If…

Machine Learning · Computer Science 2026-01-07 Raphael Ronge , Markus Maier , Frederick Eberhardt

Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whisper and HuBERT, provide an extensive evaluation of their…

Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that are both sparse and semantically meaningful. However, many…

Machine Learning · Computer Science 2025-11-06 Xiaoqing Sun , Alessandro Stolfo , Joshua Engels , Ben Wu , Senthooran Rajamanoharan , Mrinmaya Sachan , Max Tegmark
‹ Prev 1 4 5 6 7 8 10 Next ›