Salk Institute — computational neuroscience
I work in the computational neuroscience lab of Francis Crick Chair Professor Terry Sejnowski at the Salk Institute.
I work in the computational neuroscience lab of Francis Crick Chair Professor Terry Sejnowski at the Salk Institute.
I am currently extremely interested in mechanistic interpretability work and seeing where that pathway takes me. Here is a recent blog post of some results: Fork Around and Find Out (Part 2): One Head Does the Summing. Right now I am pursuing on a project investigating the internal representations of tactical motifs in transformer-based chess engines. One thing I am working on is developing and open sourcing an interactive visualizer app to aid interpretability research on transformer based chess engines:
I spent a year leveraging unsupervised learning algorithms on massive corpuses of developmental data to investigate the behavioral, neural, and genetic (GWAS) correlates of a patient subset identified by clustering on ABCD study datasets. Publication upcoming as soon as final data set is released for research from NIH.
Contributed to a graduate student’s dissertation on emotional temporal coding: multivoxel pattern analysis (MVPA) and representational similarity analysis (RSA), with region-of-interest masks in frontal pole and related areas (FSLeyes).