GPT-2

E18339

OpenAI model autoregressive language model large language model neural network transformer-based model

GPT-2 is a large transformer-based language model known for generating coherent, human-like text and sparking widespread discussion about the implications of advanced AI text generation.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

AI illustration

All labels observed (5)

Label	Occurrences
GPT-2 canonical	10
GPT2LMHeadModel	2
Language Models are Unsupervised Multitask Learners	2
GPT-2 1.5B parameter model	1
Generative Pre-trained Transformer	1

How this entity was disambiguated

This entity first appeared as the object of triple T146312 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: GPT-2
Context triple: [OpenAI, developed, GPT-2]

A. DALL·E
DALL·E is an AI model developed by OpenAI that generates images from natural language descriptions, enabling text-to-image synthesis.
B. OpenAI
OpenAI is an artificial intelligence research organization best known for developing advanced AI models such as ChatGPT and GPT series.
C. Claude
Claude is a given name most famously associated with Claude Shannon, the American mathematician and electrical engineer known as the father of information theory.
D. Google Brain
Google Brain is a deep learning research team at Google that pioneered many advances in neural networks and artificial intelligence.
E. Element AI
Element AI was a Montreal-based artificial intelligence company and research lab known for developing enterprise AI solutions and advancing deep learning research.
F. None of above. chosen
G. Unsure - the case is ambiguous/there is not enough information to decide.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: GPT-2
Target entity description: GPT-2 is a large transformer-based language model known for generating coherent, human-like text and sparking widespread discussion about the implications of advanced AI text generation.

A. DALL·E
DALL·E is an AI model developed by OpenAI that generates images from natural language descriptions, enabling text-to-image synthesis.
B. OpenAI
OpenAI is an artificial intelligence research organization best known for developing advanced AI models such as ChatGPT and GPT series.
C. Claude
Claude is a given name most famously associated with Claude Shannon, the American mathematician and electrical engineer known as the father of information theory.
D. Google Brain
Google Brain is a deep learning research team at Google that pioneered many advances in neural networks and artificial intelligence.
E. Element AI
Element AI was a Montreal-based artificial intelligence company and research lab known for developing enterprise AI solutions and advancing deep learning research.
F. None of above. chosen

Statements (53)

Predicate	Object
instanceOf	OpenAI model ⓘ autoregressive language model ⓘ large language model ⓘ neural network ⓘ transformer-based model ⓘ
announcementDate	2019-02-14 ⓘ
architectureType	decoder-only transformer ⓘ
basedOn	Transformer architecture ⓘ
contextWindowSize	1024 tokens ⓘ
developer	OpenAI ⓘ
evaluationSetting	zero-shot evaluation on downstream tasks ⓘ
framework	TensorFlow ⓘ
fullModelReleaseDate	2019-11 ⓘ
implementationLanguage	Python ⓘ
influenced	subsequent large language models ⓘ
initialReleasePolicy	partial model release ⓘ staged release ⓘ
inputType	text ⓘ
language	English ⓘ
largestVersionParameters	1.5B ⓘ
license	OpenAI model license ⓘ
notableFor	generating coherent long-form text ⓘ public debate about AI misuse risks ⓘ zero-shot performance on many NLP tasks ⓘ
notableImpact	popularized large-scale transformer language models ⓘ
openSourceImplementation	Hugging Face Transformers ⓘ
outputType	text ⓘ
paperAuthors	Alec Radford ⓘ Dario Amodei ⓘ David Luan ⓘ Ilya Sutskever ⓘ Jeff Wu ⓘ Rewon Child ⓘ
paperTitle	Language Models are Unsupervised Multitask Learners ⓘ linked to: GPT-2
parameterCount	1.5B ⓘ 117M ⓘ 345M ⓘ 774M ⓘ
predecessor	GPT ⓘ linked to: GPT-3
releaseDate	2019-02 ⓘ
safetyConcern	potential for generating misinformation ⓘ potential for impersonation ⓘ potential for spam generation ⓘ
successor	GPT-3 ⓘ
task	language modeling ⓘ text completion ⓘ text generation ⓘ zero-shot learning ⓘ
tokenizerType	Byte Pair Encoding ⓘ
trainingDataSource	WebText dataset ⓘ
trainingDataType	web pages ⓘ
trainingObjective	next token prediction ⓘ
trainingParadigm	unsupervised learning ⓘ

How these facts were elicited

Referenced by (16)

Full triples — surface form annotated when it differs from this entity's canonical label.

OpenAI → developed → GPT-2 ⓘ

OpenAI → introducedModelFamily → Generative Pre-trained Transformer ⓘ

linked to: GPT-2

GPT-2 → paperTitle → Language Models are Unsupervised Multitask Learners ⓘ

linked to: GPT-2

GPT-3 → predecessor → GPT-2 ⓘ

Rewon Child → notableWork → Language Models are Unsupervised Multitask Learners ⓘ

linked to: GPT-2

WebText → associatedWith → GPT-2 ⓘ

subject linked to: WebText dataset

Hugging Face Transformers → supportsModelType → GPT-2 ⓘ

Jeff Wu → notableWork → GPT-2 ⓘ

GPT series → hasMember → GPT-2 ⓘ

VisionEncoderDecoderModel → supportsDecoderModel → GPT2LMHeadModel ⓘ

linked to: GPT-2

EncoderDecoderModel → canUseDecoderType → GPT2LMHeadModel ⓘ

linked to: GPT-2

AutoConfig → supportsModelFamily → GPT-2 ⓘ

Language Models are Unsupervised Multitask Learners → proposesModel → GPT-2 ⓘ

Language Models are Unsupervised Multitask Learners → introduces → GPT-2 1.5B parameter model ⓘ

linked to: GPT-2

GPT → hasVersion → GPT-2 ⓘ

GPT-1 → influenced → GPT-2 ⓘ

All labels observed (5)

How this entity was disambiguated Show

Statements (53)

How these facts were elicited Show

Referenced by (16)

How this entity was disambiguated

How these facts were elicited