Data
Every table behind the figures on this site, generated at build time from the analysis files, each naming the file it came from. Nothing here is a transcription: if a number appears on a page it appears in one of these, and if it appears in one of these it was read out of the file named in the last column.
| 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, and one record per adapter with coordinates, loadings and provenance. | qwen35/fa_chart.py; results/fa_qwen35.json | 31 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
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.
How to read the cosine files
The three cosine matrices come from exact Grams: the inner products were computed on the factored LoRA form without ever materialising a dense weight-change matrix. A cosine is Gij / √(GiiGjj). The stage-one and stage-two adapters carry independent random LoRA-A draws, so trait for trait the two stages are orthogonal in coordinates even where their arrangements agree — do not read a near-zero stage-one to stage-two cosine as absence of signal. The seed floor explains why.
The persona matrix is the deployed merge, stage one at 1.0 plus stage two at 0.25, using the exact concatenation merge rather than PEFT's linear combination, which sums LoRA factors rather than deltas (the merge correction).