I am an incoming PhD student in neurosymbolic AI at the University of Amsterdam, supervised by Martha Lewis. Before that, I did my MSc in Logic and Computation at the University of Amsterdam, working with the CALM Lab, and studied Philosophy, Logic and Scientific Method at LSE.

My research asks whether large language models possess human-interpretable semantic concepts, or whether the structure we observe in their representations is something fundamentally different from how humans carve up meaning.

I study faithful concept representation in large language models using causal abstraction. Causal methods locate subspaces that are causally efficacious, but efficacy says nothing about what the subspace encodes, or the degree to which this is machine-specific.