Cover Image

Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Deng, Ruixuan, Hu, Xiaoyang, Gilberti, Miles, Storks, Shane, Taxali, Aman, Angstadt, Mike, Sripada, Chandra, Chai, Joyce
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Discovering Properties of Inflectional Morphology in Neural Emergent Communication
by: Gilberti, Miles, et al.
Published: (2025)

Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties
by: Yu, Keunwoo Peter, et al.
Published: (2023)

SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
by: Torres-Fonseca, Josue, et al.
Published: (2026)

Transparent and Coherent Procedural Mistake Detection
by: Storks, Shane, et al.
Published: (2024)

Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models
by: Bhatia, Gagan, et al.
Published: (2025)

Application of Time-Aware PC algorithm to compute Causal Functional Connectivity in Alzheimer's Disease from fMRI data
by: Biswas, Rahul, et al.
Published: (2023)

Coactive-Staggered Feature in Weyl Materials for Enhancing the Anomalous Nernst Conductivity
by: Ivanov, Vsevolod, et al.
Published: (2022)

Neurophysiological and Behavioral Effects of Micro- and Nanoplastics in Aquatic Organisms.
by: Belanger, Rachelle M, et al.
Published: (2026)

Resting‐State Coactivation Patterns of Language Reorganization in Brain Tumors
by: Antonio Napolitano, et al.
Published: (2026)

Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders
by: Deng, Boyi, et al.
Published: (2025)

Applications of Large Language Model Reasoning in Feature Generation
by: Chandra, Dharani
Published: (2025)

Revealing Multimodal Causality with Large Language Models
by: Li, Jin, et al.
Published: (2025)

Dissecting Chronos: Sparse Autoencoders Reveal Causal Feature Hierarchies in Time Series Foundation Models
by: Mishra, Anurag
Published: (2026)

Walking, Rolling, and Beyond: First-Principles and RL Locomotion on a TARS-Inspired Robot
by: Sripada, Aditya, et al.
Published: (2025)

V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models
by: Wang, Qidong, et al.
Published: (2025)

CITS: Nonparametric Statistical Causal Modeling for High-Resolution Neural Time Series
by: Biswas, Rahul, et al.
Published: (2025)

Temporally-Grounded Language Generation: A Benchmark for Real-Time Vision-Language Models
by: Yu, Keunwoo Peter, et al.
Published: (2025)

Causal Language Control in Multilingual Transformers via Sparse Feature Steering
by: Chou, Cheng-Ting, et al.
Published: (2025)

Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models
by: Ma, Ziqiao, et al.
Published: (2023)

Scene Exploration by Vision-Language Models
by: Sripada, Venkatesh, et al.
Published: (2024)

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
by: Deng, Boyi, et al.
Published: (2026)

Identifying and Mitigating Gender Cues in Academic Recommendation Letters: An Interpretability Case Study
by: Alexander, Charlotte S., et al.
Published: (2026)

Conflict Adaptation in Vision-Language Models
by: Hu, Xiaoyang
Published: (2025)

Causal Interpretation of Sparse Autoencoder Features in Vision
by: Han, Sangyu, et al.
Published: (2025)

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
by: Marks, Samuel, et al.
Published: (2024)

Dimensional Coactivation for Representational Consistency in Frozen Vision Foundation Models
by: Saddik, Izaldein Al-Zyoud Abdulmotaleb El
Published: (2026)

Can Large Language Models Infer Causal Relationships from Real-World Text?
by: Saklad, Ryan, et al.
Published: (2025)

Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations
by: Ma, Ziqiao, et al.
Published: (2024)

Leveraging Large Language Models for Rare Disease Named Entity Recognition
by: Xi, Nan Miles, et al.
Published: (2025)

Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models
by: Demircan, Can, et al.
Published: (2024)

A Large-Scale Empirical Comparison of Meta-Learners and Causal Forests for Heterogeneous Treatment Effect Estimation in Marketing Uplift Modeling
by: Singh, Aman
Published: (2026)

LinkGPT: Teaching Large Language Models To Predict Missing Links
by: He, Zhongmou, et al.
Published: (2024)

Do Language Models Encode Semantic Relations? Probing and Sparse Feature Analysis
by: Diera, Andor, et al.
Published: (2026)

Ephaptic Neuro-Modulation
by: Chawla, Aman
Published: (2025)

SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation
by: Zhao, Xinqiao, et al.
Published: (2024)

GROUNDHOG: Grounding Large Language Models to Holistic Segmentation
by: Zhang, Yichi, et al.
Published: (2024)

Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models
by: Swann, Aiden, et al.
Published: (2026)

A Survey of Pipeline Tools for Data Engineering
by: Mbata, Anthony, et al.
Published: (2024)

Improving Factual Accuracy of Neural Table-to-Text Output by Addressing Input Problems in ToTTo
by: Sundararajan, Barkavi, et al.
Published: (2024)

Input Matters: Evaluating Input Structure's Impact on LLM Summaries of Sports Play-by-Play
by: Sundararajan, Barkavi, et al.
Published: (2025)