Training a Transformer to Compose One Step Per Layer (and Proving It) — LessWrong
Summary
I'm working on an experiment comparing the internal representations of two architectures when solving a sequential algorithm, but training models to…
Description
I'm working on an experiment comparing the internal representations of two architectures when solving a sequential algorithm, but training models to…
Original reporting
AFBytes is a read-only aggregator. Use the original source for full context and complete reporting.
Open original source