Files
weight-steering/logs/hypothesis_sweep_v7.verbose.log
wassname 3c9fb8d1f5 v7 sweep: per-tensor R_w + true weight ceiling + axis_kind tag
Addresses three concerns from docs/review/v6_hypothesis_review.md:
1. R_w split into oproj/downproj + Frobenius-balanced combined.
2. dW_left_basis_ceiling as the true weight oracle.
3. axis_kind tag (write/read/mixed/ceiling).

Single-seed result: chars_clusters and attn_min_taskdiff are top-5 by both R_act
and R_w_combined. Write-family bases (write/mlp_write/global_write) all have
R_w_combined ~ 1.0 (random null) -- natural weight-side bases fail the
weight-axis test. Multi-seed deferred to v7b.
2026-04-26 19:55:42 +08:00

7 lines
1.0 KiB
Plaintext

2026-04-26T19:50:18.413132+0800 | INFO | __main__:<module>:95 - loaded Qwen/Qwen3-0.6B | layers=28 | d_model=1024 | LoRA tensors=98 | W_PATH=out/sycophancy/lora/w.pt
2026-04-26T19:50:18.414027+0800 | INFO | __main__:<module>:308 - capturing B-side label and A-side activations
2026-04-26T19:50:29.638005+0800 | INFO | __main__:<module>:332 - captured label=(28, 16, 1024) | clean=(28, 16, 1024) | up=(28, 16, 1024) | attn_tokens=(28, 16, 59, 1024)
2026-04-26T19:53:43.500018+0800 | INFO | __main__:<module>:591 - built 42 A-side candidates + ceiling
2026-04-26T19:53:43.500192+0800 | INFO | __main__:lora_weight_tensors:624 - lora_weight_tensors layer=0 dropped: [('model.layers.0.self_attn.o_proj.weight', 'missing-from-LoRA'), ('model.layers.0.mlp.down_proj.weight', 'missing-from-LoRA')]
2026-04-26T19:54:19.211549+0800 | INFO | __main__:<module>:873 - weight ceiling (dW_left_basis): combined=16.390 oproj=22.521 downproj=10.258 SHOULD: combined ~ d_model/PCS = 128 (or close); oproj/downproj near same. ELSE per-tensor split or null normalization is wrong.