English
Related papers

Related papers: Spectral Probe-Circuits: A Three-Step Recipe for I…

200 papers

Transformer language models contain localized reasoning circuits, contiguous layer blocks that improve reasoning when duplicated at inference time. Finding these circuits currently requires brute-force sweeps costing 25 GPU hours per model.…

Artificial Intelligence · Computer Science 2026-04-02 Rajkiran Panuganti

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

To help address the growing demand for ever-longer sequence lengths in transformer models, Liu et al. recently proposed Ring Attention, an exact attention algorithm capable of overcoming per-device memory bottle- necks by distributing…

Machine Learning · Computer Science 2023-11-17 William Brandon , Aniruddha Nrusimha , Kevin Qian , Zachary Ankner , Tian Jin , Zhiye Song , Jonathan Ragan-Kelley

In mechanistic interpretability, recent work scrutinizes transformer "circuits" - sparse, mono or multi layer sub computations, that may reflect human understandable functions. Yet, these network circuits are rarely acid-tested for their…

Machine Learning · Computer Science 2026-02-20 Karan Bali , Jack Stanley , Praneet Suresh , Danilo Bzdok

We present a training-free method for detecting valid mathematical reasoning in large language models through spectral analysis of attention patterns. By treating attention matrices as adjacency matrices of dynamic graphs over tokens, we…

Machine Learning · Computer Science 2026-01-05 Valentin Noël

Mechanistic interpretability aims to understand neural networks by identifying which learned features mediate specific behaviors. Attribution graphs reveal these feature pathways, but interpreting them requires extensive manual analysis --…

Computation and Language · Computer Science 2025-11-11 Giuseppe Birardi

Transformer-based language models excel at both recall (retrieving memorized facts) and reasoning (performing multi-step inference), but whether these abilities rely on distinct internal mechanisms remains unclear. Distinguishing recall…

Machine Learning · Computer Science 2026-03-16 Harshwardhan Fartale , Ashish Kattamuri , Rahul Raja , Arpita Vats , Ishita Prasad , Akshata Kishore Moharir

We introduce directional routing, a lightweight mechanism that gives each transformer attention head learned suppression directions controlled by a shared router, at 3.9% parameter cost. We train a 433M-parameter model alongside an…

Machine Learning · Computer Science 2026-03-17 Kevin Taylor

The attention mechanism is considered the backbone of the widely-used Transformer architecture. It contextualizes the input by computing input-specific attention matrices. We find that this mechanism, while powerful and elegant, is not as…

Computation and Language · Computer Science 2022-11-08 Michael Hassid , Hao Peng , Daniel Rotem , Jungo Kasai , Ivan Montero , Noah A. Smith , Roy Schwartz

Transformers have exhibited exceptional capabilities in sequence modeling tasks, leveraging self-attention and in-context learning. Critical to this success are induction heads, attention circuits that enable copying tokens based on their…

Machine Learning · Computer Science 2025-09-11 Francesco D'Angelo , Francesco Croce , Nicolas Flammarion

Transformer has become the dominant architecture for sequence modeling, yet a detailed understanding of how its structural parameters influence expressive power remains limited. In this work, we study the approximation properties of…

Machine Learning · Computer Science 2026-04-01 Penghao Yu , Haotian Jiang , Zeyu Bao , Ruoxi Yu , Qianxiao Li

Some transformer attention heads appear to function as membership testers, dedicating themselves to answering the question "has this token appeared before in the context?" We identify these heads across four language models (GPT-2 small,…

Machine Learning · Computer Science 2026-02-20 Peter Balogh

Multi-head attention, a collection of several attention mechanisms that independently attend to different parts of the input, is the key ingredient in the Transformer. Recent work has shown, however, that a large proportion of the heads in…

Computation and Language · Computer Science 2023-07-28 Jiaoda Li , Ryan Cotterell , Mrinmaya Sachan

Different transformer architectures implement identical linguistic computations via distinct connectivity patterns, yielding model imprinted ``computational fingerprints'' detectable through spectral analysis. Using graph signal processing…

Computation and Language · Computer Science 2025-10-23 Valentin Noël

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

Transformers resist surgical control. Ablating an attention head identified as critical for capitalization produces minimal behavioral change because distributed redundancy compensates for damage. This Hydra effect renders interpretability…

Machine Learning · Computer Science 2026-03-20 J. Clayton Kerce

This paper presents a spectral attention-driven reinforcement learning based intelligent method for effective and efficient detection of important signals in a wideband spectrum. In the work presented in this paper, it is assumed that the…

Signal Processing · Electrical Eng. & Systems 2020-04-02 Gihan Mendis , Jin Wei , Arjuna Madanayakey , Soumyajit Mandalz

Following the successful application of vision transformers in multiple computer vision tasks, these models have drawn the attention of the signal processing community. This is because signals are often represented as spectrograms (e.g.…

Computer Vision and Pattern Recognition · Computer Science 2022-06-22 Nicolae-Catalin Ristea , Radu Tudor Ionescu , Fahad Shahbaz Khan

Sequence modeling faces challenges in capturing long-range dependencies across diverse tasks. Recent linear and transformer-based forecasters have shown superior performance in time series forecasting. However, they are constrained by their…

Machine Learning · Computer Science 2024-11-25 Bong Gyun Kang , Dongjun Lee , HyunGi Kim , DoHyun Chung , Sungroh Yoon

Mechanistic interpretability aims to reverse-engineer large language models (LLMs) into human-understandable computational circuits. However, the complexity of pretrained models often obscures the minimal mechanisms required for specific…

Computation and Language · Computer Science 2025-10-30 Rabin Adhikari
‹ Prev 1 2 3 10 Next ›