The Visible Net is a blogging outlet for the “Academic Contingent” of mechanistic interpretability machine intelligence researchers, as well as an incubation space for the proposed National Deep Inference Facility. It is a shared blogging space for students, collaborators, and others working on mechanistic interpretability.

Contact us at info@thevisible.net, or reach out to David directly.

This project was started by David Bau, an assistant professor at Northeastern University. David’s lab focuses on understanding the interpretable mechanisms that emerge from large-scale machine learning.

The horizontal lightbulb depiction represents the emergence of ideas in a transparent setting where the internal mechanisms can all be inspected. The bulb is alight without an apparent energy source, suggesting the emergence of cognitive structure from data without explicit design.