concept
active
concept:gpt-2

GPT-2

Early large language model cited as an example of transformer-based LLMs

Neighborhood — ranked by edge-count

Concepts (2)

concept
  • GPT-4
    related_to
    Large language model underlying ChatGPT and Bing Chat; used for illustrative quotes in the paper
  • GPT-3
    related_to
    Large language model cited as an example; also used in Andreas 2022 for preliminary evidence

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • GPT-4.1concept0.838
    OpenAI model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction
  • GPT-4Vconcept0.810
    Example of unified multimodal system handling both images and text with a combined architecture
  • GPT-4 Turboconcept0.791
    OpenAI model tested; shows no alignment faking due to insufficient detailed reasoning
  • A family of large language models trained on next-token prediction, central example of simulators.
  • Is GPT an agent?question0.769
    Frequently asked question disambiguated by simulator/simulacra distinction.
  • GPT-OSS 120Bconcept0.767
    One of two large reasoning models analyzed in the paper for performative vs genuine CoT behavior
  • GPT-4 was used to generate unique variations of cheap/expensive items and room names for the test dataset
  • Disambiguation exercise.