v1v2v3 (latest)

Progress measures for grokking via mechanistic interpretability

12 January 2023

Papers citing "Progress measures for grokking via mechanistic interpretability"

50 / 125 papers shown

Title
From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers Jingtong Su Julia Kempe Karen Ullrich 14 0 0 20 Jun 2025
Hidden Breakthroughs in Language Model Training Sara Kangaslahti Elan Rosenfeld Naomi Saphra 26 0 0 18 Jun 2025
Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework Laura Kopf Nils Feldhus Kirill Bykov P. Bommer Anna Hedström Marina M.-C. Höhne Oliver Eberle 26 0 0 18 Jun 2025
Distinct Computations Emerge From Compositional Curricula in In-Context Learning Jin Hwa Lee Andrew Kyle Lampinen Aaditya K. Singh Andrew Saxe 23 0 0 16 Jun 2025
GrokAlign: Geometric Characterisation and Acceleration of Grokking Thomas Walker Ahmed Imtiaz Humayun Randall Balestriero Richard G. Baraniuk 32 0 0 14 Jun 2025
Model Organisms for Emergent Misalignment Edward Turner Anna Soligo Mia Taylor Senthooran Rajamanoharan Neel Nanda 18 1 0 13 Jun 2025
Scaling Laws for Uncertainty in Deep Learning Mattia Rosso Simone Rossi Giulio Franzese Markus Heinonen Maurizio Filippone BDL UQCV 87 0 0 11 Jun 2025
Interpreting learned search: finding a transition model and value function in an RNN that plays Sokoban Mohammad Taufeeque Aaron David Tucker Adam Gleave Adrià Garriga-Alonso 35 0 0 11 Jun 2025
On Finetuning Tabular Foundation Models Ivan Rubachev Akim Kotelnikov Nikolay Kartashev Artem Babenko 29 0 0 10 Jun 2025
Enhancing Accuracy and Maintainability in Nuclear Plant Data Retrieval: A Function-Calling LLM Approach Over NL-to-SQL Mishca de Costa Muhammad Anwar Dave Mercier Mark Randall Issam Hammad 26 0 0 10 Jun 2025
Addition in Four Movements: Mapping Layer-wise Information Trajectories in LLMs Yao Yan 13 0 0 09 Jun 2025
Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs Roy Eisenstadt Itamar Zimerman Lior Wolf LRM 15 0 0 08 Jun 2025
Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks D. Kunin Giovanni Luca Marchetti F. Chen Dhruva Karkada James B. Simon M. DeWeese Surya Ganguli Nina Miolane 28 0 0 06 Jun 2025
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Seongmin Lee Aeree Cho Grace C. Kim ShengYun Peng Mansi Phute Duen Horng Chau LM&MA AI4CE 72 0 0 05 Jun 2025
Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Bhavik Chandna Zubair Bashir Procheta Sen 87 0 0 05 Jun 2025
Bridging Neural ODE and ResNet: A Formal Error Bound for Safety Verification Abdelrahman Sayed Sayed Pierre-Jean Meyer Mohamed Ghazel 29 0 0 03 Jun 2025
Tug-of-war between idiom's figurative and literal meanings in LLMs Soyoung Oh Xinting Huang Mathis Pink Michael Hahn Vera Demberg 64 0 0 02 Jun 2025
Circuit Stability Characterizes Language Model Generalization Alan Sun LRM 22 0 0 30 May 2025
Continuous Chain of Thought Enables Parallel Exploration and Reasoning Halil Alperen Gozeten M. E. Ildiz Xuechen Zhang Hrayr Harutyunyan A. S. Rawat Samet Oymak LRM 67 0 0 29 May 2025
Characterising the Inductive Biases of Neural Networks on Boolean Data Chris Mingard Lukas Seier Niclas Goring Andrei-Vlad Badelita Charles London Ard A. Louis AI4CE 37 0 0 29 May 2025
How Do Transformers Learn Variable Binding in Symbolic Programs? Yiwei Wu Atticus Geiger Raphaël Millière NAI 28 1 0 27 May 2025
From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Stanley Yu Vaidehi Bulusu Oscar Yasunaga Clayton Lau Cole Blondin Sean O'Brien Kevin Zhu Vasu Sharma 54 0 0 27 May 2025
Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability? Yongjie Wang Yibo Wang Xin Zhou Zhiqi Shen 62 0 0 24 May 2025
Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models Patrick Leask Neel Nanda Noura Al Moubayed 87 1 0 23 May 2025
The emergence of sparse attention: impact of data distribution and benefits of repetition Nicolas Zucchet Francesco dÁngelo Andrew Kyle Lampinen Stephanie C. Y. Chan 214 1 0 23 May 2025
Mechanistic evaluation of Transformers and state space models Aryaman Arora Neil Rathi Nikil Roashan Selvam Róbert Csordás Dan Jurafsky Christopher Potts 114 1 0 21 May 2025
Beyond the Black Box: Interpretability of LLMs in Finance Hariom Tatsat Ariye Shater AIFin 66 0 0 14 May 2025
Understanding In-context Learning of Addition via Activation Subspaces Xinyan Hu Kayo Yin Michael I. Jordan Jacob Steinhardt Lijie Chen 145 2 0 08 May 2025
Contextures: Representations from Contexts Runtian Zhai Kai Yang Che-Ping Tsai Burak Varici Zico Kolter Pradeep Ravikumar 447 0 0 02 May 2025
A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i Kola Ayonrinde Louis Jaburi MILM 175 1 0 01 May 2025
Reinforcement Learning for Reasoning in Large Language Models with One Training Example Yiping Wang Qing Yang Zhiyuan Zeng Liliang Ren Liu Liu ... Jianfeng Gao Weizhu Chen Shuaiqiang Wang Simon Shaolei Du Yelong Shen OffRL ReLM LRM 332 47 0 29 Apr 2025
Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers Roman Abramov Felix Steinbauer Gjergji Kasneci 467 0 0 29 Apr 2025
Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video Sonia Joseph Praneet Suresh Lorenz Hufe Edward Stevinson Robert Graham Yash Vadi Danilo Bzdok Sebastian Lapuschkin Lee Sharkey Blake A. Richards 151 0 0 28 Apr 2025
MIB: A Mechanistic Interpretability Benchmark Aaron Mueller Atticus Geiger Sarah Wiegreffe Dana Arad Iván Arcuschin ... Alessandro Stolfo Martin Tutek Amir Zur David Bau Yonatan Belinkov 116 2 0 17 Apr 2025
Towards Combinatorial Interpretability of Neural Computation Micah Adler Dan Alistarh Nir Shavit FAtt 393 2 0 10 Apr 2025
Capturing AI's Attention: Physics of Repetition, Hallucination, Bias and Beyond Frank Yingjie Huo Neil F. Johnson 126 1 0 06 Apr 2025
Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction Junlang Qian Zixiao Zhu Hanzhang Zhou Zijian Feng Zepeng Zhai K. Mao AAML VLM 125 0 0 04 Apr 2025
LLM Social Simulations Are a Promising Research Method Jacy Reese Anthis Ryan Liu Sean M. Richardson Austin C. Kozlowski Bernard Koch James A. Evans Erik Brynjolfsson Michael S. Bernstein ALM 111 15 0 03 Apr 2025
Low Rank and Sparse Fourier Structure in Recurrent Networks Trained on Modular Addition Akshay Rangamani 103 0 0 28 Mar 2025
TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research Philip Quirke Clement Neo Abir Harrasse Dhruv Nathawani Luke Marks Amir Abdullah 86 0 0 17 Mar 2025
Implicit Reasoning in Transformers is Reasoning through Shortcuts Tianhe Lin Jian Xie Siyu Yuan Deqing Yang ReLM LRM 153 3 0 10 Mar 2025
Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking) Yoonsoo Nam Seok Hyeong Lee Clementine Domine Yea Chan Park Charles London Wonyl Choi Niclas Goring Seungjai Lee AI4CE 209 1 0 28 Feb 2025
Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification Vishnu Kabir Chhabra Ding Zhu Mohammad Mahdi Khalili 99 2 0 27 Feb 2025
Do Multilingual LLMs Think In English? Lisa Schut Y. Gal Sebastian Farquhar 88 15 0 24 Feb 2025
Entropy-Lens: The Information Signature of Transformer Computations Riccardo Ali Francesco Caso Christopher Irwin Pietro Lio 103 3 0 23 Feb 2025
An explainable transformer circuit for compositional generalization Cheng Tang Brenden Lake Mehrdad Jazayeri LRM 149 3 0 19 Feb 2025
Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization Yunzhe Hu Difan Zou Dong Xu 157 1 0 17 Feb 2025
Early Stopping Against Label Noise Without Validation Data Suqin Yuan Lei Feng Tongliang Liu NoLa 279 19 0 11 Feb 2025
Constrained belief updates explain geometric structures in transformer representations Mateusz Piotrowski P. Riechers Daniel Filan A. Shai 128 2 0 04 Feb 2025
Modular Training of Neural Networks aids Interpretability Satvik Golechha Maheep Chaudhary Joan Velja Alessandro Abate Nandi Schoots 153 0 0 04 Feb 2025