← Search

Hoagy Cunningham

2 accepted papers

2026

Constitutional Classifiers++: Production-Grade Defenses against Universal Jailbreaks

ICLR 2026poster

We introduce enhanced Constitutional Classifiers that deliver production-grade jailbreak robustness with dramatically reduced computational costs and refusal rates compared to previous-generation defenses. We first identify vulnerabilities in existing systems that evaluate model outputs without rega…

Cited by 0SourceScholar
2024

Sparse Autoencoders Find Highly Interpretable Features in Language Models

ICLR 2024poster

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise, human-understandable explanations for what neural networks ar…