English
Related papers

Related papers: Interpretability-Guided Layer Selection over Subsp…

200 papers

Model internals encode rich information about how a large language model (LLM) processes its training data; however, post-training data engineering largely relies on external signals and ignores rich intrinsic signals lying in model…

Machine Learning · Computer Science 2026-05-27 Yi Jing , Zao Dai , Jinwu Hu , Zijun Yao , Lei Hou , Juanzi Li , Xiaozhi Wang

Sparse autoencoders (SAEs) have emerged as a promising approach in language model interpretability, offering unsupervised extraction of sparse features. For interpretability methods to succeed, they must identify abstract features across…

Machine Learning · Computer Science 2025-09-08 Lovis Heindrich , Philip Torr , Fazl Barez , Veronika Thost

Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed a variety of representation-based…

Computation and Language · Computer Science 2025-03-05 Zhengxuan Wu , Aryaman Arora , Atticus Geiger , Zheng Wang , Jing Huang , Dan Jurafsky , Christopher D. Manning , Christopher Potts

Large-scale text-to-image diffusion models have become the backbone of modern image editing, yet text prompts alone do not offer adequate control over the editing process. Two properties are especially desirable: disentanglement, where…

Graphics · Computer Science 2025-10-07 Ronen Kamenetsky , Sara Dorfman , Daniel Garibi , Roni Paiss , Or Patashnik , Daniel Cohen-Or

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 shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models, demonstrating their…

Machine Learning · Computer Science 2024-08-06 Charles O'Neill , Christine Ye , Kartheik Iyer , John F. Wu

Improving Sparse Autoencoders (SAEs) requires benchmarks that can precisely validate architectural innovations. However, current SAE benchmarks on LLMs are often too noisy to differentiate architectural improvements, and current synthetic…

Machine Learning · Computer Science 2026-02-17 David Chanin , Adrià Garriga-Alonso

Sparse autoencoders (SAEs) have recently emerged as pivotal tools for introspection into large language models. SAEs can uncover high-quality, interpretable features at different levels of granularity and enable targeted steering of the…

Information Retrieval · Computer Science 2026-01-19 Martin Spišák , Ladislav Peška , Petr Škoda , Vojtěch Vančura , Rodrigo Alves

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

Sparse autoencoders (SAEs) are a recent technique for decomposing neural network activations into human-interpretable features. However, in order for SAEs to identify all features represented in frontier models, it will be necessary to…

Machine Learning · Computer Science 2025-06-04 Anish Mudide , Joshua Engels , Eric J. Michaud , Max Tegmark , Christian Schroeder de Witt

Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structure is typically…

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

Recent work on sparse autoencoders (SAEs) has shown promise in extracting interpretable features from neural networks and addressing challenges with polysemantic neurons caused by superposition. In this paper, we apply SAEs to the early…

Machine Learning · Computer Science 2024-09-10 Liv Gorton

Sparse Autoencoders (SAEs) aim to decompose the activation space of large language models (LLMs) into human-interpretable latent directions or features. As we increase the number of features in the SAE, hierarchical features tend to split…

Computation and Language · Computer Science 2025-11-18 David Chanin , James Wilken-Smith , Tomáš Dulka , Hardik Bhatnagar , Satvik Golechha , Joseph Bloom

LLMs are increasingly being used in healthcare. This promises to free physicians from drudgery, enabling better care to be delivered at scale. But the use of LLMs in this space also brings risks; for example, such models may worsen existing…

Machine Learning · Computer Science 2026-03-03 Hiba Ahsan , Byron C. Wallace

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

The evaluation of large language models (LLMs) relies heavily on standardized benchmarks. These benchmarks provide useful aggregated metrics for a given capability, but those aggregated metrics can obscure (i) particular sub-areas where the…

Computation and Language · Computer Science 2025-12-25 Matyas Bohacek , Nino Scherrer , Nicholas Dufour , Thomas Leung , Christoph Bregler , Stephanie C. Y. Chan

The ability of large language models (LLMs) to follow instructions is crucial for their practical applications, yet the underlying mechanisms remain poorly understood. This paper presents a novel framework that leverages sparse autoencoders…

Machine Learning · Computer Science 2025-02-18 Zirui He , Haiyan Zhao , Yiran Qiao , Fan Yang , Ali Payani , Jing Ma , Mengnan Du

Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising…

Computation and Language · Computer Science 2026-02-27 Usha Bhalla , Alex Oesterling , Claudio Mayrink Verdun , Himabindu Lakkaraju , Flavio P. Calmon

Reward models (RMs) are critical components of alignment pipelines, yet they exhibit biases toward superficial stylistic cues, preferring better-presented responses over semantically superior ones. Existing debiasing methods typically…

Computation and Language · Computer Science 2026-03-16 Mengyuan Sun , Zhuohao Yu , Weizheng Gu , Shikun Zhang , Wei Ye

Sparse autoencoders (SAEs) are widely used to extract sparse, interpretable latents from transformer activations. We test whether commonly used SAE quality metrics and automatic explanation pipelines can distinguish trained transformers…

Machine Learning · Computer Science 2026-01-28 Thomas Heap , Tim Lawson , Lucy Farnik , Laurence Aitchison