Brown et al. (arXiv v1, 2020) report using the same model and architecture as GPT-2, with alternating dense and locally banded sparse attention.
One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.
What it connects
Language Models are Few-Shot Learners → reports using method from → Language Models are Unsupervised Multitask Learners
Where it appears
No collection page holds this claim. It is listed with its records in the explorer.