I'm a visual neuroscientist currently working as an AI Safety Fellow at Anthropic, taking a temporary hiatus from working as a postdoctoral research scientist in the Kriegeskorte Lab. In my work, I use neuroimaging and deep learning methods to study how intelligent visual systems, whether biological or artificial, can flexibly encode and combine different features of their visual experience to subserve adaptive behavior. Additionally, I maintain an open-source Python package, TorchLens, for inspecting and intervening on the internals of neural network models (ideally any neural network whatsoever).

I did my PhD in the Harvard Vision Lab, working with Yaoda Xu. Before that, I studied face processing as a lab manager for Gregory McCarthy, and self-control in capuchin monkeys as an undergrad with Laurie Santos.

Contact: johnmarkedwardtaylor(AT)gmail.com