most citedCan sparse autoencoders be used to decompose and interpret steering vectors?

1 citations · 1 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CL2025

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

Andrew M. Bean, Ryan Othniel Kearns, Angelika Romanou +39

Evaluating large language models (LLMs) is crucial for both assessing their capabilities and identifying safety or robustness issues prior to deployment. Reliably measuring abstrac…

cs.LG2025

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations

Harry Mayne, Ryan Othniel Kearns, Yushi Yang +4

To collaborate effectively with humans, language models must be able to explain their decisions in natural language. We study a specific type of self-explanation: self-generated co…

cs.LG2025

Collapse of Irrelevant Representations (CIR) Ensures Robust and Non-Disruptive LLM Unlearning

Filip Sondej, Yushi Yang

Current unlearning and safety training methods consistently fail to remove dangerous knowledge from language models. We identify the root cause - unlearning targets representations…

cs.LG2025

Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization

Filip Sondej, Yushi Yang, Mikołaj Kniejski +1

Language models can retain dangerous knowledge and skills even after extensive safety fine-tuning, posing both misuse and misalignment risks. Recent studies show that even speciali…

cs.LG20241 cited

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

Harry Mayne, Yushi Yang, Adam Mahdi

Steering vectors are a promising approach to control the behaviour of large language models. However, their underlying mechanisms remain poorly understood. While sparse autoencoder…

cs.LG2024

How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis

Yushi Yang, Filip Sondej, Harry Mayne +2

Safety fine-tuning algorithms reduce harmful outputs in language models, yet their mechanisms remain under-explored. Direct Preference Optimization (DPO) is a popular choice of alg…