Data
Every table behind the site, as CSV and JSON. Each names the file it came from.
what is this?
Everything the pages draw from, as CSV and JSON, generated at build time from the analysis files. Each file names its source. If a number appears on a page, it is in one of these.
| File | What it is | Built from | Size |
|---|---|---|---|
| traits.csv | One row per adapter: provenance, Big Five keying, the five factor-chart coordinates, the five oblimin loadings, chart length and communality. | qwen35/fa_chart.py over results/gram_sweep.npz; results/fa_qwen35.json | 24 kB |
| cosines_stage1.csv | The 134×134 matrix of cosines between the stage1 adapters, from the exact Gram. | qwen35/results/gram_sweep.npz | 131 kB |
| cosines_stage2.csv | The 134×134 matrix of cosines between the stage2 adapters, from the exact Gram. | qwen35/results/gram_stage2.npz | 125 kB |
| cosines_persona.csv | The 134×134 matrix of cosines between the persona adapters, from the exact Gram. | qwen35/results/gram_personas.npz | 128 kB |
| judged_means.csv | Blind Big Five means, 1 to 7, per trait and condition (base, stage one, persona), averaged over 24 prompts at build time. | qwen35/phase10_runs/judged_100.json#records | 14 kB |
| steering_means.csv | Blind Big Five means against steering dose for each of the thirteen steered directions, averaged over 24 prompts at build time. | qwen35/phase10_runs/judged_steerfix23.json#records | 5 kB |
| factors.csv | The five factors: sum of squared oblimin loadings and Tucker congruence with each Goldberg keying target. | qwen35/results/fa_qwen35.json#solutions.centred_k5 | 1 kB |
| chart.json | Everything the chart draws: factor metadata, the axis list, and one record per adapter with its five chart coordinates, its six component scores, its loadings and its provenance. | qwen35/fa_chart.py; results/fa_qwen35.json; analysis/blog_data.json | 39 kB |
| stages.json | The five chart coordinates of all 134 adapters at each stage of training, each stage charted in its own Gram by the identical construction. | qwen35/fa_chart.py over results/gram_sweep.npz, gram_stage2.npz, gram_personas.npz | 23 kB |
| neighbours.json | The twelve nearest and six farthest adapters to each trait in each of the three Grams, with each trait's mean cosine to the other 133. | qwen35/results/gram_sweep.npz, gram_stage2.npz, gram_personas.npz | 170 kB |
| stage2.json | The stage-two steering generations at every dose for the shared direction and its two controls, with the per-dose text statistics. | qwen35/phase10_runs/steer_results_s2mean.json, _s2balanced.json; analysis/s2mean_steer_stats.json | 279 kB |
| traits.json | The trait index used by the search on the traits page. | qwen35/results/fa_qwen35.json | 15 kB |
The primary artefacts
The adapters, on Hugging Face.
The adapters
All 134 traits in three forms — the stage-one DPO adapter, the stage-two introspection adapter and the exact persona merge — plus the null control arms and the seven later traits.
The wiki
The complete record: 282 pages, every number with its source file and JSON key, every claim marked current, superseded, unconfirmed or withdrawn, and a page per trait that goes well beyond what this site shows.