English
Related papers

Related papers: Beyond Components: Singular Vector-Based Interpret…

200 papers

Decoder-only transformers lead to a step-change in capability of large language models. However, opinions are mixed as to whether they are really planning or reasoning. A path to making progress in this direction is to study the model's…

Machine Learning · Computer Science 2025-02-14 Andrew Cohen , Andrey Gromov , Kaiyu Yang , Yuandong Tian

Though vision transformers (ViTs) have achieved state-of-the-art performance in a variety of settings, they exhibit surprising failures when performing tasks involving visual relations. This begs the question: how do ViTs attempt to perform…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Michael A. Lepori , Alexa R. Tartaglini , Wai Keen Vong , Thomas Serre , Brenden M. Lake , Ellie Pavlick

Code language models excel on code intelligence tasks, yet their internal interpretability is underexplored. Existing neuron interpretability techniques from NLP are suboptimal for source code due to programming languages formal,…

Software Engineering · Computer Science 2026-03-20 Zhe Yin , Xiaodong Gu , Beijun Shen

The Transformer architecture has inarguably revolutionized deep learning, overtaking classical architectures like multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs). At its core, the attention block differs in form and…

Machine Learning · Computer Science 2025-03-18 Weronika Ormaniec , Felix Dangel , Sidak Pal Singh

The development of effective explainability tools for Transformers is a crucial pursuit in deep learning research. One of the most promising approaches in this domain is Layer-wise Relevance Propagation (LRP), which propagates relevance…

Machine Learning · Computer Science 2025-06-04 Yarden Bakish , Itamar Zimerman , Hila Chefer , Lior Wolf

Transformers have dominated empirical machine learning models of natural language processing. In this paper, we introduce basic concepts of Transformers and present key techniques that form the recent advances of these models. This includes…

Computation and Language · Computer Science 2023-11-30 Tong Xiao , Jingbo Zhu

Large language models (LLMs) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how neural networks…

Computation and Language · Computer Science 2026-02-13 Usman Naseem

A major goal of neuroscience is to understand brain computations during visual processing in naturalistic settings. A dominant approach is to use image-computable deep neural networks trained with different task objectives as a basis for…

Neurons and Cognition · Quantitative Biology 2026-02-06 Hossein Adeli , Sun Minni , Nikolaus Kriegeskorte

Attention-based architectures have become ubiquitous in machine learning, yet our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their…

Machine Learning · Computer Science 2023-08-02 Yihe Dong , Jean-Baptiste Cordonnier , Andreas Loukas

Transformers are a widespread and successful model architecture, particularly in Natural Language Processing (NLP) and Computer Vision (CV). The essential innovation of this architecture is the Attention Mechanism, which solves the problem…

Machine Learning · Computer Science 2024-11-25 Bernhard Bermeitinger , Tomas Hrycej , Massimo Pavone , Julianus Kath , Siegfried Handschuh

Driven by the appealing properties of neural fields for storing and communicating 3D data, the problem of directly processing them to address tasks such as classification and part segmentation has emerged and has been investigated in recent…

Computer Vision and Pattern Recognition · Computer Science 2024-01-31 Adriano Cardace , Pierluigi Zama Ramirez , Francesco Ballerini , Allan Zhou , Samuele Salti , Luigi Di Stefano

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

Standard transformers entangle all computation in a single residual stream, obscuring which components perform which functions. We introduce the Dual-Stream Transformer, which decomposes the residual stream into two functionally distinct…

Computation and Language · Computer Science 2026-03-10 J. Clayton Kerce , Alexis Fox

The greatest ambition of mechanistic interpretability is to completely rewrite deep neural networks in a format that is more amenable to human understanding, while preserving their behavior and performance. In this paper, we attempt to…

Machine Learning · Computer Science 2025-02-03 Gonçalo Paulo , Nora Belrose

Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features. However, many neurons exhibit $\textit{mixed selectivity}$, i.e., they represent multiple unrelated features. A…

Machine Learning · Statistics 2023-10-19 David Klindt , Sophia Sanborn , Francisco Acosta , Frédéric Poitevin , Nina Miolane

As AI systems are used in high-stakes applications, ensuring interpretability is crucial. Mechanistic Interpretability (MI) aims to reverse-engineer neural networks by extracting human-understandable algorithms to explain their behavior.…

Machine Learning · Computer Science 2025-03-03 Maxime Méloux , Silviu Maniu , François Portet , Maxime Peyrard

Mechanistic interpretability aims to understand the inner workings of large neural networks by identifying circuits, or minimal subgraphs within the model that implement algorithms responsible for performing specific tasks. These circuits…

Machine Learning · Computer Science 2024-12-06 Jatin Nainani , Sankaran Vaidyanathan , AJ Yeung , Kartik Gupta , David Jensen

Classifying images with an interpretable decision-making process is a long-standing problem in computer vision. In recent years, Prototypical Part Networks has gained traction as an approach for self-explainable neural networks, due to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Zhijie Zhu , Lei Fan , Maurice Pagnucco , Yang Song

While the successes of transformers across many domains are indisputable, accurate understanding of the learning mechanics is still largely lacking. Their capabilities have been probed on benchmarks which include a variety of structured and…

Machine Learning · Computer Science 2023-07-25 Yuchen Li , Yuanzhi Li , Andrej Risteski

We present and evaluate a technique for computing path-sensitive interference conditions during abstract interpretation of concurrent programs. In lieu of fixed point computation, we use prime event structures to compactly represent causal…

Programming Languages · Computer Science 2017-05-02 Marcelo Sousa , César Rodríguez , Vijay D'Silva , Daniel Kroening