Analyzing the Structure of Attention in a Transformer Language Model — mentioned by versteegen

Mon, 06 Feb 2023 03:25:01 GMT

See my reply to sibling: https://news.ycombinator.com/item?id=34672865 A more interesting example of transformers learning a process may be [1]. There's a large literature on applying language models to reasoning tasks, but not many on what's actually going on inside them. But see for example [2]. Also https://transformer-circuits.pub/ has a body of work on it, but still at a very early stage (see in particular "In-context Learning and Induction Heads"). [1] Extraction of organic chemistry grammar from unsupervised learning of chemical reactions…

Paper and discussion history. A mention is not an endorsement.

Analyzing the Structure of Attention in a Transformer Language Model · HackerPapers discussions

Analyzing the Structure of Attention in a Transformer Language Model — mentioned by versteegen