Cover Image

Feature Rivalry in Sparse Autoencoder Representations: A Mechanistic Study of Uncertainty-Driven Feature Competition in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Harshavardhan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MoRFI: Monotonic Sparse Autoencoder Feature Identification
by: Dimakopoulos, Dimitris, et al.
Published: (2026)

Sparse Autoencoder Features for Classifications and Transferability
by: Gallifant, Jack, et al.
Published: (2025)

Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders
by: Chanin, David, et al.
Published: (2025)

Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts
by: Yan, Xinyuan, et al.
Published: (2025)

Improving Steering Vectors by Targeting Sparse Autoencoder Features
by: Chalnev, Sviatoslav, et al.
Published: (2024)

PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
by: Koromilas, Panagiotis, et al.
Published: (2026)

Tracking the Feature Dynamics in LLM Training: A Mechanistic Study
by: Xu, Yang, et al.
Published: (2024)

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
by: Chanin, David, et al.
Published: (2025)

AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features
by: Zhu, Xudong, et al.
Published: (2025)

Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction
by: Sainsbury, Chris, et al.
Published: (2026)

Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders
by: Zheng, Carolina, et al.
Published: (2025)

PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders
by: Frikha, Ahmed, et al.
Published: (2025)

Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering
by: Bakman, Yavuz, et al.
Published: (2025)

Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders
by: Patel, Het, et al.
Published: (2026)

Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders
by: He, Zhengfu, et al.
Published: (2024)

SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection
by: Zhang, Huopu, et al.
Published: (2025)

Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders
by: Lan, Michael, et al.
Published: (2024)

Time-Aware Feature Selection: Adaptive Temporal Masking for Stable Sparse Autoencoder Training
by: Li, T. Ed, et al.
Published: (2025)

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
by: Wang, Xu, et al.
Published: (2026)

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

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies
by: Cho, Seonglae, et al.
Published: (2025)

Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models
by: Yamashita, Tomoya, et al.
Published: (2025)

Enhancing In-Hospital Mortality Prediction Using Multi-Representational Learning with LLM-Generated Expert Summaries
by: Battula, Harshavardhan, et al.
Published: (2024)

Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders
by: Li, Aaron J., et al.
Published: (2025)

Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features
by: Cho, Seonglae, et al.
Published: (2026)

ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
by: Butler, Landon, et al.
Published: (2025)

How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders
by: Inaba, Tatsuro, et al.
Published: (2025)

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
by: Minegishi, Gouki, et al.
Published: (2025)

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
by: Li, Yuhui, et al.
Published: (2024)

Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines
by: Jørgensen, Mikkel Godsk, et al.
Published: (2026)

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
by: Song, Xiangchen, et al.
Published: (2025)

Psychological Profiling in Cybersecurity: A Look at LLMs and Psycholinguistic Features
by: Tshimula, Jean Marie, et al.
Published: (2024)

Training Superior Sparse Autoencoders for Instruct Models
by: Li, Jiaming, et al.
Published: (2025)

AlignSAE: Concept-Aligned Sparse Autoencoders
by: Yang, Minglai, et al.
Published: (2025)

Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders
by: Zhang, Ruikang, et al.
Published: (2026)

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

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks
by: Karvonen, Adam, et al.
Published: (2024)

Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders
by: Kurochkin, Vadim, et al.
Published: (2025)

Binary Autoencoder for Mechanistic Interpretability of Large Language Models
by: Cho, Hakaze, et al.
Published: (2025)

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
by: Karvonen, Adam, et al.
Published: (2025)