Methods › Natural Language Processing › Transformers › GPT-3

GPT-3

1,906 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

GPT-3 is an autoregressive transformer model with 175 billion parameters. It uses the same architecture/model as GPT-2, including the modified initialization, pre-normalization, and reversible tokenization, with the exception that GPT-3 uses alternating dense and locally banded sparse attention patterns in the layers of the transformer, similar to the Sparse Transformer.

Source: Language Models are Few-Shot LearnersSee Code · EleutherAI/gpt-neox

Papers archive 2025-07-28

30 shown of 1,906, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 665 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Language Modelling363
Language Modeling265
Question Answering206
Large Language Model187
Retrieval128
In-Context Learning115
Text Generation103
Prompt Engineering88
Code Generation80
Few-Shot Learning78
Sentence75
Math61
Retrieval-augmented Generation59
RAG58
Decision Making54
Multiple-choice54
Hallucination45
Benchmarking43
Zero-Shot Learning42
Natural Language Understanding40

Usage over time archive 2025-07-28

Papers per year tagged with GPT-3: 2020 to 2025, peak 744 744 0 2020: 16 papers 2020 2021: 99 papers 2021 2022: 219 papers 2022 2023: 744 papers 2023 2024: 716 papers 2024 2025: 112 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (1,906 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Transformers

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections