wassname fe562c2b5c antipasto_ablate: warm-start lora_c from S-space output variance ...

group_init now seeds each lora_c to the top-k principal axes of the S-space
output coords h=diag(S)Vh x (highest-energy output dirs => largest loss-grad on
the ablation strength), so lora_c starts in a high-gradient region not random.
Cheap r x r second moment when not orienting; reuses Sigma xx^T when cov_orient.
Benchmark always calibrates ablate now. This is the data-variance direction, not
a contrastive behavior dir (SFT has no pos/neg split) -- noted in the docstring.

UAT: |cos(lora_c, top output-PC)| = 1.0000 vs ~0.35 chance; smoke green.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

2026-06-17 18:18:32 +08:00

..

_cost.py

benchmark sweep: rot(U/both) ablation, whitening conclusion, cost rows

2026-06-17 06:17:53 +08:00

cost_report.py

variants: replace arrow's dense block with diagonal-plus-low-rank core

2026-06-15 20:13:15 +08:00

metamath_gsm8k_benchmark.py

antipasto_ablate: warm-start lora_c from S-space output variance

2026-06-17 18:18:32 +08:00