Joseph Bloom
UKAISI
UKAISI
Joseph Bloom is Head of Model Transparency at the UK AI Security Institute, where he works at the intersection of Loss-of-Control risks, monitorability and interpretability. His team recently published on Auditing Games for Sandbagging. Joseph was mentored by Neel Nanda in MATS 5.0 cohort. Joseph was previously the maintainer of the TransformerLens package, authored the SAE Lens package and published A is for Absorption as a LASR mentor. Joseph has a double degree in Computational Biology and Statistics from the University of Melbourne.
The Summer 2024 cohort marked a significant expansion, supporting approximately 90 scholars with 40 mentors—the broadest mentor selection in MATS history. This cohort incorporated MATS as a 501(c)(3) nonprofit organization, formalizing its institutional structure. The program expanded its research portfolio to include at least four governance mentors alongside technical research streams, reflecting growing interest in AI policy and technical governance work. The 10-week research phase continued in Berkeley, with scholars conducting work across mechanistic interpretability, evaluations, scalable oversight, and governance research.Notable outputs from this cohort include research on targeted manipulation and deception in LLMs trained on user feedback, which was accepted to NeurIPS workshops, and contributions to an AI safety via debate paper that won best paper at ICML 2024. One scholar co-founded Decode Research, a new AI safety organization focused on building interpretability tools.
Joseph Bloom
