Lee Sharkey

Goodfire AI

Principal Investigator

Links

Focus

Interpretability

Lee Sharkey is a Principle Investigator at Goodfire.

His team has focused on improved interpretability methods, including parameter decomposition methods such as Attribution-based Parameter Decomposition and Stochastic Parameter Decomposition and adVersarial Parameter Decomposition).

Previously, Lee was Chief Strategy Officer and cofounder of Apollo Research, and a Research Engineer at Conjecture, where he worked on sparse autoencoders as a solution to representational superposition.