{"id":15709,"date":"2021-10-27T12:19:33","date_gmt":"2021-10-27T16:19:33","guid":{"rendered":"https:\/\/www.bu.edu\/cs\/?post_type=profile&p=15709"},"modified":"2026-04-01T10:43:46","modified_gmt":"2026-04-01T14:43:46","slug":"gabriel-franco","status":"publish","type":"profile","link":"https:\/\/www.bu.edu\/cs\/profiles\/gabriel-franco\/","title":{"rendered":"Gabriel Franco"},"content":{"rendered":"

Gabriel Franco is a fifth-year Computer Science Ph.D. candidate at Boston University, advised by Prof. Mark Crovella. Before joining BU, he earned his BSc and MSc from the Federal University of Vi\u00e7osa in Brazil, advised by Prof. Giovanni Comarela.<\/p>\n

His primary research focuses on the mechanistic interpretability of large language models (LLMs). He develops methods to uncover the causal drivers of model behavior, with a particular interest in the low-rank signals that arise within the attention mechanism.<\/p>\n

Website<\/h3>\n

https:\/\/cs-people.bu.edu\/gvfranco\/<\/a><\/p>\n","protected":false},"author":17043,"template":"","_links":{"self":[{"href":"https:\/\/www.bu.edu\/cs\/wp-json\/wp\/v2\/profile\/15709"}],"collection":[{"href":"https:\/\/www.bu.edu\/cs\/wp-json\/wp\/v2\/profile"}],"about":[{"href":"https:\/\/www.bu.edu\/cs\/wp-json\/wp\/v2\/types\/profile"}],"author":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cs\/wp-json\/wp\/v2\/users\/17043"}],"version-history":[{"count":3,"href":"https:\/\/www.bu.edu\/cs\/wp-json\/wp\/v2\/profile\/15709\/revisions"}],"predecessor-version":[{"id":23070,"href":"https:\/\/www.bu.edu\/cs\/wp-json\/wp\/v2\/profile\/15709\/revisions\/23070"}],"wp:attachment":[{"href":"https:\/\/www.bu.edu\/cs\/wp-json\/wp\/v2\/media?parent=15709"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}