Cover Image

Can sparse autoencoders be used to decompose and interpret steering vectors?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mayne, Harry, Yang, Yushi, Mahdi, Adam
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations
by: Mayne, Harry, et al.
Published: (2025)

How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis
by: Yang, Yushi, et al.
Published: (2024)

Negation Neglect: When models fail to learn negations in training
by: Mayne, Harry, et al.
Published: (2026)

Collapse of Irrelevant Representations (CIR) Ensures Robust and Non-Disruptive LLM Unlearning
by: Sondej, Filip, et al.
Published: (2025)

Multi-view autoencoders for Fake News Detection
by: Pereira, Ingryd V. S. T., et al.
Published: (2025)

Toward universal steering and monitoring of AI models
by: Beaglehole, Daniel, et al.
Published: (2025)

Scaling and evaluating sparse autoencoders
by: Gao, Leo, et al.
Published: (2024)

Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization
by: Sondej, Filip, et al.
Published: (2025)

Efficient semantic uncertainty quantification in language models via diversity-steered sampling
by: Park, Ji Won, et al.
Published: (2025)

PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners
by: Xiao, Yijia, et al.
Published: (2023)

Steering CLIP's vision transformer with sparse autoencoders
by: Joseph, Sonia, et al.
Published: (2025)

Scaling sparse feature circuit finding for in-context learning
by: Kharlapenko, Dmitrii, et al.
Published: (2025)

Agentic-imodels: Evolving agentic interpretability tools via autoresearch
by: Singh, Chandan, et al.
Published: (2026)

SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?
by: Kirchhof, Michael, et al.
Published: (2025)

Applying sparse autoencoders to unlearn knowledge in language models
by: Farrell, Eoin, et al.
Published: (2024)

Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environments
by: Mannekote, Amogh, et al.
Published: (2024)

LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit
by: Gong, Ruihao, et al.
Published: (2024)

From communities to interpretable network and word embedding: an unified approach
by: Prouteau, Thibault, et al.
Published: (2024)

Surrogate modeling for interpreting black-box LLMs in medical predictions
by: Han, Changho, et al.
Published: (2026)

A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
by: Mayne, Harry, et al.
Published: (2026)

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
by: Chen, Jianhui, et al.
Published: (2024)

LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
by: Wu, Yuhao, et al.
Published: (2025)

AcquisitionSynthesis: Targeted Data Generation using Acquisition Functions
by: Agarwal, Ishika, et al.
Published: (2026)

ExpertLens: Activation steering features are highly interpretable
by: Fedzechkina, Masha, et al.
Published: (2025)

MIMIC-RD: Can LLMs differentially diagnose rare diseases in real-world clinical settings?
by: AlDin, Zilal Eiz, et al.
Published: (2025)

Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders
by: Wang, Xu, et al.
Published: (2025)

Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation
by: Dong, Harry, et al.
Published: (2024)

LinkQ: An LLM-Assisted Visual Interface for Knowledge Graph Question-Answering
by: Li, Harry, et al.
Published: (2024)

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

Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?
by: Sun, Yiyou, et al.
Published: (2025)

Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
by: Wang, Shouren, et al.
Published: (2025)

IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector
by: Chen, Zheng, et al.
Published: (2025)

RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation
by: Nikdan, Mahdi, et al.
Published: (2024)

ECO: Quantized Training without Full-Precision Master Weights
by: Nikdan, Mahdi, et al.
Published: (2026)

Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods
by: Dhaini, Mahdi, et al.
Published: (2025)

Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation
by: Manvi, Rohin, et al.
Published: (2024)

Fine-Tuning Small Language Models (SLMs) for Autonomous Web-based Geographical Information Systems (AWebGIS)
by: Ashani, Mahdi Nazari, et al.
Published: (2025)

When Can Transformers Count to n?
by: Yehudai, Gilad, et al.
Published: (2024)

Can LLMs Follow Simple Rules?
by: Mu, Norman, et al.
Published: (2023)

Post-Trained MoE Can Skip Half Experts via Self-Distillation
by: Lv, Xingtai, et al.
Published: (2026)