Architectures · intermediate · concept 58 of 176
GPT (Generative Pre-trained Transformer)
A decoder-only Transformer trained to predict the next token. Each GPT generation, from GPT-1 through GPT-5 and beyond, showed that scaling this simple idea produces increasingly capable AI. The architecture behind ChatGPT.
Key terms
AutoregressiveNext-token predictionDecoder-onlyScaling laws
Learn these first
Videos
▶ Deep Dive into LLMs like ChatGPT ↗
Andrej Karpathy · YouTube
▶ Large Language Models explained briefly ↗
3Blue1Brown · YouTube
Guides and articles
Courses, papers, and more
This unlocks