NeurIPS 2025 Workshop MechInterp Submissions

Representation Similarity Reveals Implicit Layer Grouping in Neural Networks
Tian Gao, Amit Dhurandhar, Karthikeyan Natesan Ramamurthy, Dennis Wei
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Detecting Motivated Reasoning in the Internal Representations of Language Models
Parsa Mirtaheri, Mikhail Belkin
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Shared Memorization Structures in Transformers Revealed by Loss Curvature
Jack Merullo, Srihita Vatsavaya, Owen Lewis
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Correlations in the Data Lead to Semantically Rich Feature Geometry Under Superposition
Lucas Prieto, Edward Stevinson, Melih Barsbey, Tolga Birdal, Pedro A. M. Mediano
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Spotlight
- Readers: Everyone
Enforcing Orderedness in SAEs to Improve Feature Consistency
Sophie L. Wang, Alex Quach, Nithin Parsan, John Jingxuan Yang
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Towards a Mechanistic Understanding of Robustness in Finetuned Reasoning Models
Aashiq Muhamed, Xuandong Zhao, Mona T. Diab, Virginia Smith, Dawn Song
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Spotlight
- Readers: Everyone
Attention Pattern Discovery at Scale
Jonathan Katzy, Razvan Mihai Popescu, Erik Mekkes, Arie van Deursen, Maliheh Izadi
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Composable Sparse Subnetworks via Maximum-Entropy Principle
Francesco Caso, Samuele Fonio, Nicola Saccomanno, Simone Monaco, Fabrizio Silvestri
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Spectral Dynamics in Neural Network Training: Mathematical Foundations for Understanding Representational Development
Brian Richard Olsen, Sam Fatehmanesh, Frank Xiao, Adarsh Kumarappan, Anirudh Gajula
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition
Zhengfu He, Junxuan Wang, Rui Lin, Xuyang Ge, Wentao Shu, Qiong Tang, Junping Zhang, Xipeng Qiu
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Spotlight
- Readers: Everyone
Evaluating Explanatory Evaluations: An Explanatory Virtues Framework for Mechanistic Interpretability
Kola Ayonrinde, Louis Jaburi
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Model Diffing without Borders: Unlocking Cross-Architecture Model Diffing to Reveal Hidden Ideological Alignment in Llama and Qwen
Thomas Jiralerspong, Trenton Bricken
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Spotlight
- Readers: Everyone
Dual Mechanisms of Value Expression: Decomposing Intrinsic and Prompted Values in Language Models
Jongwook Han, Jongwon Lim, InJin Kong, Yohan Jo
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Steering Evaluation-Aware Language Models to Act Like They Are Deployed
Tim Tian Hua, Andrew Qin, Samuel Marks, Neel Nanda
- Published: 30 Sept 2025, Last Modified: 24 Oct 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
From Tokens to Semantics: The Emergence and Stabilization of Polysemanticity in Language Models
Jonas Rohweder, Aiden Zhou, Aniruddhan Ramesh, Sharvil Limaye, Akshay Bhaskar, Ashwinee Panda, Vasu Sharma
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts
Xinyuan Yan, Shusen Liu, Kowshik Thopalli, Bei Wang Phillips
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Emergent World Beliefs: Exploring Transformers in Stochastic Games
Adam Kamel, Tanish Rastogi, Michael Ma, Kailash Ranganathan
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Mitigating Emergent Misalignment with Data Attribution
Louis Jaburi, Gonçalo Paulo, Stepan Shabalin, Lucia Quirke, Nora Belrose
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders
David Chanin, Tomáš Dulka, Adrià Garriga-Alonso
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality
Lingjing Kong, Shaoan Xie, Guangyi Chen, Yuewen Sun, Xiangchen Song, Eric P. Xing, Kun Zhang
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Rethinking Crowd-Sourced Evaluation of Neuron Explanations
Tuomas Oikarinen, Ge Yan, Akshay R. Kulkarni, Tsui-Wei Weng
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Mitigating Sycophancy in Language Models via Sparse Activation Fusion and Multi-Layer Activation Steering
Pyae Phoo Min, Avigya Paudel, Naufal Adityo, Arthur Zhu, Andrew Rufail, Cole Blondin, Kevin Zhu, Sunishchal Dev, Sean O'Brien
- Published: 30 Sept 2025, Last Modified: 29 Oct 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Attention Layers Add Into Low-Dimensional Residual Subspaces
Junxuan Wang, Xuyang Ge, Wentao Shu, Zhengfu He, Xipeng Qiu
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone
Scratchpad Thinking: Alternation Between Storage and Computation in Latent Reasoning Models
Brad Peters, Sayam Goyal, María Emilia Granda, Akshath Vijayakumar Narmadha, Dharunish Yugeswardeenoo, Callum Stuart McDougall, Sean O'Brien, Ashwinee Panda, Kevin Zhu, Cole Blondin
- Published: 30 Sept 2025, Last Modified: 30 Sept 2025
- Mech Interp Workshop (NeurIPS 2025) Spotlight
- Readers: Everyone
Causal Discovery and Inference through Next-Token Prediction
Eivinas Butkus, Nikolaus Kriegeskorte
- Published: 30 Sept 2025, Last Modified: 22 Oct 2025
- Mech Interp Workshop (NeurIPS 2025) Poster
- Readers: Everyone