In this paper, we identify and characterize the emerging area of representation engineering
(RepE), an approach to enhancing the transparency of AI systems that draws on insights
from cognitive neuroscience. RepE places population-level representations, rather than
neurons or circuits, at the center of analysis, equipping us with novel methods for monitoring
and manipulating high-level cognitive phenomena in deep neural networks (DNNs). We
provide baselines and an initial analysis of RepE techniques, showing that they offer simple …