One-dimensional vs multi-dimensional features in interpretability
February 01, 2025
How to stop conflating with 768 dimensions
LLMs are really good at k-order thinking (where k is even)
January 15, 2025
You still need to tell a language model you want to cure cancer before it can help you cure cancer.
Information bounds in quantum gravity
January 13, 2025
How information theory links quantum mechanics and general relativity
Can quantised autoencoders find and interpret circuits in language models?
March 01, 2024
Using VQ-VAEs and categorical decision trees to do automatic circuit identification in LLMs.
Learning compressed representations and GPT-5 speculation
March 01, 2024
Why language models probably get too much from the abstraction we give them for free