About
Hello, I’m Gerard Boxó.
I am currently pursuing a Master’s degree in Bioinformatics in Barcelona. My primary area of interest is Mechanistic Interpretability (MI), where I investigate how machine learning models, both LLMs and BIOML, can be made more transparent and understandable.
This blog serves as a documentation of my journey, where I share experiments, insights, and detailed analyses of significant MI research papers.
My goal is to provide valuable information for to anyone interested in Mechanistic Interpretability. I encourage you to explore the content, leave comments, and connect with me as I continue my learning journey.