Neuronpedia is a free and open source platform for AI interpretability. It may be a nice way at getting at the layer activations that I’ve been looking for.

• Graph of “The woman walked into the room”
• API docs
• Github

Tasks

• Set up the example chapters in the ACM book format
• Cleaning/Organizing
• 7:00 – 7:45 showing
• Pick up Barbara 9:50

SBIRs

• 9:00 standup
• More runs started
• Start looking at how to run UMAP across multiple pickle files. Probably just iterate over the files to create the mapping and save it, then a second stage to calculate the mapped points
• Send the Gemini analysis to Clay and CC Aaron