Pilot summary — pilot_tier0_opseq_451ef5087182
Generated 2026-11-09T06:54:13+00:00 on device mps; config hash 451ef5087182; seeds [0, 1, 2].
Gate B — donor/recipient gap (final-answer exact match, mean over seeds; CI = cluster bootstrap on programs)
| split | chance | donor mean (sd) | recipient mean (sd) | paired gap seed 0 [95% CI] |
|---|---|---|---|---|
| target_iid | 0.105 | 1.000 (0.000) | 0.092 (0.053) | +0.847 [+0.825, +0.870] |
| control_iid | 0.129 | 1.000 (0.000) | 1.000 (0.000) | +0.000 [+0.000, +0.000] |
| comp_heldout | 0.110 | 1.000 (0.000) | 0.450 (0.032) | +0.513 [+0.468, +0.560] |
| len_ood | 0.140 | 0.086 (0.017) | 0.091 (0.016) | -0.002 [-0.034, +0.032] |
Ω-step accuracy on target_iid (token emitted at the first Ω step): donor 1.000, recipient 0.062.
Gate C — hook no-op checks (bitwise equality of logits on 256 dev items)
| model | repeat | capture-all | disabled hook | enabled zero hook changes output |
|---|---|---|---|---|
| donor_s0 | True | True | True | True |
| recipient_s0 | True | True | True | True |
| donor_s1 | True | True | True | True |
| recipient_s1 | True | True | True | True |
| donor_s2 | True | True | True | True |
| recipient_s2 | True | True | True | True |
RQ1 — within-donor localization of Ω (n = 490 clean/corrupt pairs, read position = r1, predicting r2)
Baselines: s0: clean 1.000, sham (corrupt run scored on clean answer) 0.000; s1: clean 1.000, sham (corrupt run scored on clean answer) 0.000; s2: clean 1.000, sham (corrupt run scored on clean answer) 0.000
Mean restored-answer rate after patching the clean activation into the corrupted run (rows = layers, columns = positions , v0, op1, Ω, op3, =, r1):
resid_post: L0: 0.00 0.00 0.00 0.00 0.00 0.00 1.00 | L1: 0.00 0.00 0.00 0.00 0.00 0.00 1.00 | L2: 0.00 0.00 0.00 0.00 0.00 0.00 1.00 | L3: 0.00 0.00 0.00 0.00 0.00 0.00 1.00attn_out: L0: 0.00 0.00 0.00 0.00 0.00 0.00 1.00 | L1: 0.00 0.00 0.00 0.00 0.00 0.00 0.00 | L2: 0.00 0.00 0.00 0.00 0.00 0.00 0.00 | L3: 0.00 0.00 0.00 0.00 0.00 0.00 0.00mlp_out: L0: 0.00 0.00 0.00 0.00 0.00 0.00 1.00 | L1: 0.00 0.00 0.00 0.00 0.00 0.00 0.90 | L2: 0.00 0.00 0.00 0.00 0.00 0.00 0.83 | L3: 0.00 0.00 0.00 0.00 0.00 0.00 0.17
Reproducibility: resid_post_s0_repeat_max_abs_diff = 0.0000; attn_out_s0_repeat_max_abs_diff = 0.0000; mlp_out_s0_repeat_max_abs_diff = 0.0000; resid_post_s1_repeat_max_abs_diff = 0.0000; attn_out_s1_repeat_max_abs_diff = 0.0000; mlp_out_s1_repeat_max_abs_diff = 0.0000; resid_post_s2_repeat_max_abs_diff = 0.0000; attn_out_s2_repeat_max_abs_diff = 0.0000; mlp_out_s2_repeat_max_abs_diff = 0.0000; resid_post_across_seed_pearson_min = 1.0000; attn_out_across_seed_pearson_min = 1.0000; mlp_out_across_seed_pearson_min = 0.9642
Figures: fig_gap_tier0.pdf, fig_localization_ablation_tier0.pdf, fig_localization_heads_tier0.pdf, fig_localization_patching_tier0.pdf
Interpretation (observed vs. speculative)
Observed: the numbers above are produced by the artifacts listed in the manifest. Any statement about transfer is out of scope for this run: no transplant was performed. Speculative: whether the localized positions/layers constitute a transferable 'organ' is the object of the next experiment (activation graft with sham/random controls).