conftrace_

sparse autoencoder

112 papers

Explore in graph

Co-occurring keywords

large language model (13587) mechanistic interpretability (133) feature extraction (1580) language model (4599) representation learning (6206) model interpretability (519) steering vector (33) feature steering (6) feature decomposition (51) interpretable feature (23)

Papers

ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders AAAI 2026

SCOPE: Intrinsic Semantic Space Control for Mitigating Copyright Infringement in LLMs AAAI 2026

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering EACL 2026

Feature Integration Spaces: Joint Training Reveals Dual Encoding in Neural Network Representations AAAI 2026

Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction AAAI 2026

Interpretable Reward Model via Sparse Autoencoder AAAI 2026

Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders EACL 2026

SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models EACL 2026

Evaluating Sparse Autoencoders for Monosemantic Representation EACL 2026

Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story EACL 2026

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders AAAI 2026

SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder AAAI 2026

Efficient Transcoder Adaptation for Fine-Tuned Models: Revealing Medical Reasoning Mechanisms in Large Language Models AAAI 2026

Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs AAAI 2026

Measuring Mechanistic Independence: Can Bias Be Removed Without Erasing Demographics? EACL 2026

Steering Large Language Models for Machine Translation Personalization EACL 2026

Out of Distribution, Out of Luck: Process Rewards Misguide Reasoning Models EACL 2026

Evaluating the Impact of SAE-based Language Steering on LLM Performance EACL 2026

The Unintended Trade-off of AI Alignment: Balancing Hallucination Mitigation and Safety in LLMs EACL 2026

Unveiling Decision-Making in LLMs for Text Classification : Extraction of influential and interpretable concepts with Sparse Autoencoders EACL 2026

AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders EACL 2026

Feature Drift: How Fine-Tuning Repurposes Representations in LLMs EACL 2026

SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination WACV 2026

Leveraging Sparsity for Privacy in Collaborative Inference WACV 2026

Beyond I’m Sorry, I Can’t: Dissecting Large-Language-Model Refusal AAAI 2026