Daily Notes
A note on a note on mechanistic interpretability, variables, and importance of interpretable bases
Linear Decoding and Deep Nets with Neural Collapse
Masked Language Modeling
Notes on Toy Models of Superposition
Some definitions in Information Theory
Paper Reading
How Does Information Bottleneck Help Deep Learning?
Language Models for Text Classification: Is In-Context Learning Enough?
Large Language Models Struggle to Learn Long-Tail Knowledge
Akash Sharma
Search
Search
Search
Dark mode
Light mode
Paper Reading
Jul 09, 2024
How Does Information Bottleneck Help Deep Learning?
Jun 29, 2024
Language Models for Text Classification: Is In-Context Learning Enough?
Jun 17, 2024
Large Language Models Struggle to Learn Long-Tail Knowledge