Nashville AI/ML Reading Group

👋 Welcome to Nashville’s AI/ML Reading Group!
Hey y’all, today we will be covering a interesting explainable AI paper from Anthropic. Anthropic has open-source their interpretable AI framework here https://github.com/safety-research/circuit-tracer!

🔗 Meeting link

Google Link: https://meet.google.com/swk-qjjn-miu

📄 Paper in review

Title: Circuit Tracing: Revealing Computational Graphs in Language Models

Authors: Anthropic
Link: https://transformer-circuits.pub/2025/attribution-graphs/methods.html

Presenter: Alexy Skoutnev

See you Thursday!

Best regards,
Alexy Skoutnev
Organizer, Nashville AI/ML Reading Group