English
Related papers

Related papers: Sparse Feature Circuits: Discovering and Editing I…

200 papers

This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…

Computation and Language · Computer Science 2024-05-22 Charles O'Neill , Thang Bui

Sparse dictionary learning has been a rapidly growing technique in mechanistic interpretability to attack superposition and extract more human-understandable features from model activations. We ask a further question based on the extracted…

Machine Learning · Computer Science 2024-02-20 Zhengfu He , Xuyang Ge , Qiong Tang , Tianxiang Sun , Qinyuan Cheng , Xipeng Qiu

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

A widely used strategy to discover and understand language model mechanisms is circuit analysis. A circuit is a minimal subgraph of a model's computation graph that executes a specific task. We identify a gap in existing circuit discovery…

Machine Learning · Computer Science 2025-02-10 Tal Haklay , Hadas Orgad , David Bau , Aaron Mueller , Yonatan Belinkov

Finding human-understandable circuits in language models is a central goal of the field of mechanistic interpretability. We train models to have more understandable circuits by constraining most of their weights to be zeros, so that each…

Machine Learning · Computer Science 2025-11-18 Leo Gao , Achyuta Rajaram , Jacob Coxon , Soham V. Govande , Bowen Baker , Dan Mossing

Transformer-based models have become state-of-the-art tools in various machine learning tasks, including time series classification, yet their complexity makes understanding their internal decision-making challenging. Existing…

Machine Learning · Computer Science 2025-11-27 Matīss Kalnāre , Sofoklis Kitharidis , Thomas Bäck , Niki van Stein

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…

Machine Learning · Computer Science 2023-10-05 Hoagy Cunningham , Aidan Ewart , Logan Riggs , Robert Huben , Lee Sharkey

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

To date, most discoveries of network subcomponents that implement human-interpretable computations in deep vision models have involved close study of single units and large amounts of human labor. We explore scalable methods for extracting…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Achyuta Rajaram , Neil Chowdhury , Antonio Torralba , Jacob Andreas , Sarah Schwettmann

A fundamental question in interpretability research is to what extent neural networks, particularly language models, implement reusable functions through subnetworks that can be composed to perform more complex tasks. Recent advances in…

Machine Learning · Computer Science 2025-06-24 Philipp Mondorf , Sondre Wold , Barbara Plank

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

Which components in transformer language models are responsible for discourse understanding? We hypothesize that sparse computational graphs, termed as discursive circuits, control how models process discourse relations. Unlike simpler…

Computation and Language · Computer Science 2025-10-14 Yisong Miao , Min-Yen Kan

Mechanistic interpretability seeks to reverse-engineer neural network computations into human-understandable algorithms, yet extracting sparse computational circuits from billion-parameter language models remains challenging due to…

Machine Learning · Computer Science 2026-01-21 Mohammed Mudassir Uddin , Shahnawaz Alam , Mohammed Kaif Pasha

Sparse neural networks are often hypothesized to be more interpretable than dense models, motivated by findings that weight sparsity can produce compact circuits in language models. However, it remains unclear whether structural sparsity…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Siyu Zhang

Explaining why a language model produces a particular output requires local, input-level explanations. Existing methods uncover global capability circuits (e.g., indirect object identification), but not why the model answers a specific…

Artificial Intelligence · Computer Science 2025-09-30 Tung-Yu Wu , Fazl Barez

We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-loss objective, we show on models up to 7B parameters that…

Machine Learning · Computer Science 2026-05-26 Florent Draye , Anson Lei , Hsiao-Ru Pan , Ingmar Posner , Bernhard Schölkopf

Circuit analysis of any certain model behavior is a central task in mechanistic interpretability. We introduce our circuit discovery pipeline with Sparse Autoencoders (SAEs) and a variant called Transcoders. With these two modules inserted…

Machine Learning · Computer Science 2024-07-23 Xuyang Ge , Fukang Zhu , Wentao Shu , Junxuan Wang , Zhengfu He , Xipeng Qiu

Understanding the internal circuits that language models use to solve tasks remains a central challenge in mechanistic interpretability. A crucial part of finding circuits is understanding why each attention head attends where it does. To…

Machine Learning · Computer Science 2026-05-15 Gabriel Franco , Lucas M. Tassis , Azalea Rohr , Mark Crovella

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Wei-Lun Chao , Tanya Berger-Wolf , Yu Su

Sparse attention has been claimed to increase model interpretability under the assumption that it highlights influential inputs. Yet the attention distribution is typically over representations internal to the model rather than the inputs…

Computation and Language · Computer Science 2021-06-09 Clara Meister , Stefan Lazov , Isabelle Augenstein , Ryan Cotterell
‹ Prev 1 2 3 10 Next ›