English
Related papers

Related papers: Automatically Interpreting Millions of Features in…

200 papers

Sparse autoencoders (SAEs) enable interpretability research by decomposing entangled model activations into monosemantic features. However, under what circumstances SAEs derive most fine-grained latent features for safety, a low-frequency…

Machine Learning · Computer Science 2026-04-15 Jiaqi Weng , Han Zheng , Hanyu Zhang , Ej Zhou , Qinqin He , Jialing Tao , Hui Xue , Zhixuan Chu , Xiting Wang

Deep generative models like VAEs and diffusion models have advanced various generation tasks by leveraging latent variables to learn data distributions and generate high-quality samples. Despite the field of explainable AI making strides in…

Machine Learning · Computer Science 2025-12-22 Mengdan Zhu , Raasikh Kanjiani , Jiahui Lu , Andrew Choi , Qirui Ye , Liang Zhao

Deep learning weather prediction models achieve remarkable predictive skill yet remain largely opaque: we know little about how they represent physical climate phenomena internally. Mechanistic interpretability through Sparse Autoencoders…

Machine Learning · Computer Science 2026-05-19 Minjong Cheon

Adapting foundation models for specific purposes has become a standard approach to build machine learning systems for downstream applications. Yet, it is an open question which mechanisms take place during adaptation. Here we develop a new…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Hyesu Lim , Jinho Choi , Jaegul Choo , Steffen Schneider

Sparse autoencoders (SAEs) trained on large language model activations output thousands of features that enable mapping to human-interpretable concepts. The current practice for analyzing these features primarily relies on inspecting…

Computation and Language · Computer Science 2026-03-26 Wilson E. Marcílio-Jr , Danilo M. Eler

While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptual distinction that reconciles competing narratives…

Machine Learning · Computer Science 2025-07-01 Kenny Peng , Rajiv Movva , Jon Kleinberg , Emma Pierson , Nikhil Garg

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

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 for transformer-based language models are typically defined independently per layer. In this work we analyze statistical relationships between features in adjacent layers to understand how features evolve through a…

Machine Learning · Computer Science 2024-11-19 Daniel Balcells , Benjamin Lerner , Michael Oesterle , Ediz Ucar , Stefan Heimersheim

Sparse autoencoders (SAEs) are widely used to extract human-interpretable features from neural network activations, but their learned features can vary substantially across random seeds and training choices. To improve stability, we studied…

Machine Learning · Statistics 2026-03-05 Piotr Jedryszek , Oliver M. Crook

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

SAEs have recently been employed as a promising unsupervised approach for understanding the representations of layers of Large Language Models (LLMs). However, with the growth in model size and complexity, training SAEs is computationally…

Computation and Language · Computer Science 2025-09-23 Davide Ghilardi , Federico Belotti , Marco Molinari , Tao Ma , Matteo Palmonari

Artificial neural networks that can recover latent dynamics from recorded neural activity may provide a powerful avenue for identifying and interpreting the dynamical motifs underlying biological computation. Given that neural variance…

Neurons and Cognition · Quantitative Biology 2023-07-03 Andrew R. Sedler , Christopher Versteeg , Chethan Pandarinath

Sparse Autoencoders (SAEs) can efficiently identify candidate monosemantic features from pretrained neural networks for galaxy morphology. We demonstrate this on Euclid Q1 images using both supervised (Zoobot) and new self-supervised (MAE)…

Instrumentation and Methods for Astrophysics · Physics 2025-11-13 John F. Wu , Michael Walmsley

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) 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

A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make fine-grained circuit analysis on transformer-based language…

Machine Learning · Computer Science 2024-11-08 Jacob Dunefsky , Philippe Chlenski , Neel Nanda

Sparse autoencoders (SAEs) are increasingly used for safety-relevant applications including alignment detection and model steering. These use cases require SAE latents to be as atomic as possible. Each latent should represent a single…

Machine Learning · Computer Science 2026-04-07 Matthew Levinson

The general-purpose nature of Large Language Models (LLMs) presents a significant challenge for domain-specific applications, often leading to out-of-domain (OOD) interactions that undermine the provider's intent. Existing methods for…

Artificial Intelligence · Computer Science 2026-05-13 Elias Shaheen , Avi Mendelson

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
‹ Prev 1 8 9 10 Next ›