English
Related papers

Related papers: Scaling sparse feature circuit finding for in-cont…

200 papers

Sparse Autoencoders (SAEs) are a promising approach for extracting neural network representations by learning a sparse and overcomplete decomposition of the network's internal activations. However, SAEs are traditionally trained considering…

Machine Learning · Computer Science 2025-04-02 Jeffrey Olmo , Jared Wilson , Max Forsey , Bryce Hepner , Thomas Vin Howe , David Wingate

Sparse Autoencoder (SAE) features have become essential tools for mechanistic interpretability research. SAE features are typically characterized by examining their activating examples, which are often "monosemantic" and align with human…

Artificial Intelligence · Computer Science 2025-09-30 Claire Tian , Katherine Tian , Nathan Hu

Sparse Autoencoders (SAEs) have emerged as a powerful tool for interpreting the internal representations of CLIP vision encoders, yet existing analyses largely focus on the semantic meaning of individual features. We introduce information…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Yusung Ro , Jaehyun Choi , Junmo Kim

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

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…

Machine Learning · Computer Science 2025-10-10 Yifei Yao , Mengnan Du

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

Large Language Models (LLMs) frequently exhibit strong translation abilities, even without task-specific fine-tuning. However, the internal mechanisms governing this innate capability remain largely opaque. To demystify this process, we…

Computation and Language · Computer Science 2026-01-19 Xinwei Wu , Heng Liu , Xiaohu Zhao , Yuqi Ren , Linlong Xu , Longyue Wang , Deyi Xiong , Weihua Luo , Kaifu Zhang

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

Machine Learning · Computer Science 2026-03-17 Thibault Formal , Maxime Louis , Hervé Dejean , Stéphane Clinchant

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

In-Context Learning (ICL) enables transformer-based language models to adapt to new tasks by conditioning on demonstration examples. However, traditional example-driven in-context learning lacks explicit modules for knowledge retrieval and…

Computation and Language · Computer Science 2026-03-31 Pan Chen , Shaohong Chen , Mark Wang , Shi Xuan Leong , Priscilla Fung , Varinia Bernales , Alan Aspuru-Guzik

Identifying the features learned by neural networks is a core challenge in mechanistic interpretability. Sparse autoencoders (SAEs), which learn a sparse, overcomplete dictionary that reconstructs a network's internal activations, have been…

Machine Learning · Computer Science 2024-05-27 Dan Braun , Jordan Taylor , Nicholas Goldowsky-Dill , Lee Sharkey

Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features activate, not which change model outputs when amplified. We introduce Control Reinforcement…

Machine Learning · Computer Science 2026-05-05 Seonglae Cho , Zekun Wu , Adriano Koshiyama

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

A common goal of mechanistic interpretability is to decompose the activations of neural networks into features: interpretable properties of the input computed by the model. Sparse autoencoders (SAEs) are a popular method for finding these…

Machine Learning · Computer Science 2025-02-10 Patrick Leask , Bart Bussmann , Michael Pearce , Joseph Bloom , Curt Tigges , Noura Al Moubayed , Lee Sharkey , Neel Nanda

Sparse autoencoders (SAEs) are widely used in mechanistic interpretability research for large language models; however, the state-of-the-art method of using $k$-sparse autoencoders lacks a theoretical grounding for selecting the…

Machine Learning · Computer Science 2025-08-11 Sewoong Lee , Adam Davies , Marc E. Canby , Julia Hockenmaier

Sparse autoencoders (SAEs) are a popular method for decomposing Large Langage Models (LLM) activations into interpretable latents. However, due to their substantial training cost, most academic research uses open-source SAEs which are only…

Machine Learning · Computer Science 2025-06-13 Patrick Leask , Neel Nanda , Noura Al Moubayed

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…

Machine Learning · Computer Science 2025-11-11 Zhen Xu , Zhen Tan , Song Wang , Kaidi Xu , Tianlong Chen

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

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques such as \textit{sparse…

Computation and Language · Computer Science 2026-02-02 Aryaman Arora , Zhengxuan Wu , Jacob Steinhardt , Sarah Schwettmann

We identify semantically coherent, context-consistent network components in large language models (LLMs) using coactivation of sparse autoencoder (SAE) features collected from just a handful of prompts. Focusing on concept-relation…

Computation and Language · Computer Science 2026-04-21 Ruixuan Deng , Xiaoyang Hu , Miles Gilberti , Shane Storks , Aman Taxali , Mike Angstadt , Chandra Sripada , Joyce Chai