Understanding the Parameter Decomposition papers Understanding attribution-based and stochastic parameter decomposition methods Jul 06, 2025 |
What's different about a Matryoshka SAE? Brief notes from the Matryoshka SAEs paper. Jun 30, 2025 |
10 Autoencoders in a Trenchcoat, part 1 Notes on the core sections of Anthropic's Toy Models of Superposition. Jun 25, 2025 |
Notes on "A Mathematical Framework for Transformer Circuits" Close-reading a classic interpretability paper and trying to make sense of it Jun 14, 2025 |
Four Papers: Align and Translate, Seq2Seq, Pointer Networks, and Attention My notes from the third meeting of the 90/30 Club, a paper-reading club (open to everyone!) in SF. May 19, 2025 |
Trying to figure out how to set up a transformer in pytorch, before I knew any ML or pytorch. Aug 30, 2024 |
Information theory and statistics Notes on the basics of information theory Aug 17, 2024 |
Formal models of decision-making Incomplete notes on decision theory. Aug 15, 2024 |
A started-but-not-nearly-finished set of notes on sorting algorithms. Aug 15, 2024 |
Algorithmic information theory and friends Incomplete notes from when I was younger on algorithmic information theory. Aug 15, 2024 |
Notes on set theory and the foundations of math Basic notes from getting comfortable with thinking about sets. Feb 24, 2024 |