Loading...
Loading...
Contributors:
Dataset URI:
10.5281/zenodo.23365351Prompts, model responses, blind-coding files, pre-registrations, code and outputs for fifteen experiments testing introspection, retention and the self-model in language models structure by structure (Claude Opus 5 / 5.5, Sonnet 5.5, Haiku 4.5 / 5.5; Qwen2.5-1.5B/3B with LoRA fine-tuning and hidden-state probes; small networks trained from scratch). Includes every Claude instance transcript per experiment (pilot, pre-registered Series B at n = 30 per condition, robustness checks in four wordings, follow-ups), Series B registration and blind-coder files, open-model and small-model code and results, and a script that recomputes every statistics table of the paper from raw counts (Wilson, Newcombe, Fisher, sign test, Holm). LoRA adapter weights are not included and can be regenerated with the code. Personal data were removed. See README.md.
Keyword(s):
introspection; self-report; language models; phenomenology; retention; self-model; replication; pre-registration.
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
No Associated Publication Data Available
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)