8 citations · 11 across the 4 of their papers we have counts for
4 papers
Evolution of SAE Features Across Layers in LLMs
Daniel Balcells, Benjamin Lerner, Michael Oesterle +2
Sparse Autoencoders for transformer-based language models are typically defined independently per layer. In this work we analyze statistical relationships between features in adjac…
Data Science as a Route to AI for Middle- and High-School Students
Shriram Krishnamurthi, Emmanuel Schanzer, Joe Gibbs Politz +3
The Bootstrap Project's Data Science curriculum has trained about 100 teachers who are using it around the country. It is specifically designed to aid adoption at a wide range of i…
Event Loops as First-Class Values: A Case Study in Pedagogic Language Design
Joe Politz, Benjamin Lerner, Sorawee Porncharoenwase +1
The World model is an existing functional input-output mechanism for event-driven programming. It is used in numerous popular textbooks and curricular settings. The World model con…
Synthesis of Recursive ADT Transformations from Reusable Templates
Jeevana Priya Inala, Nadia Polikarpova, Xiaokang Qiu +2
Recent work has proposed a promising approach to improving scalability of program synthesis by allowing the user to supply a syntactic template that constrains the space of potenti…