diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-08 01:31:16 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-08 01:31:16 -0500 |
| commit | 02252d942dbf449276059c49260ec0994c4f9a5d (patch) | |
| tree | c9460204ffdfd451018ac6da2e040cac99e12da2 /results/gelu_ablation/relu_dfa_s456.json | |
| parent | 3b3557286af7fe9f7376e1e6122169ce8b0a17b1 (diff) | |
3-seed multi-seed verification of penalized DFA deep cos = +0.17
| seed | l0 | l1 | l2 | l3 | l4 | layer-mean |
|---|---:|---:|---:|---:|---:|---:|
| 42 | +0.316 | +0.169 | +0.151 | +0.165 | +0.166 | +0.193 |
| 123 | +0.333 | +0.093 | +0.155 | +0.178 | +0.177 | +0.187 |
| 456 | +0.339 | +0.131 | +0.123 | +0.150 | +0.150 | +0.179 |
3-seed mean deep cos (l1-l4): ~0.155 ± 0.025
3-seed layer-mean: +0.186 ± 0.007
The +0.17 finding is rock-solid, combined with:
- null calibration: training-Bs +0.16 vs fresh-Bs +0.002
- hypothesis B confirmed: vanilla early ep deep cos ~0
- 3-seed reproducibility (this commit)
This is the §4 evidence for the paper's 'penalty creates partial deep
alignment, partially alleviating mode 2'.
Diffstat (limited to 'results/gelu_ablation/relu_dfa_s456.json')
0 files changed, 0 insertions, 0 deletions