summaryrefslogtreecommitdiff
path: root/results
diff options
context:
space:
mode:
authorYurenHao0426 <Blackhao0426@gmail.com>2026-04-08 17:31:09 -0500
committerYurenHao0426 <Blackhao0426@gmail.com>2026-04-08 17:31:09 -0500
commit61d483e429f4fead0e44805eba0f643b7464c6e9 (patch)
tree41c207ba3412928d564da7418b113831696478ef /results
parent4b731f824e4a4ee8606aa472a9e5adc4021991b8 (diff)
paper v2.30: fix layer-0 cosine numbers + add per-seed appendix M
Found a numerical error in §4 ¶3: the layer-0 vanilla DFA cosines were listed as +0.42, +0.45, +0.39 across seeds 42/123/456 but the actual re-measurement on the saved early-epoch checkpoints gives +0.421, +0.436, +0.418 (the s456 value was off by 0.03). The deep-mean numbers in Table 2 (-0.008 ± 0.013) were already correct. Changes: - §4 ¶3: layer-0 trio updated to +0.42, +0.44, +0.42 across seeds and cite now points to a new per-seed appendix. - New Appendix M (Layer-0 Dominance): 6-row table of per-seed per-layer cosines on vanilla DFA early checkpoints (3 seeds × ep 1, 2), with per-layer ||g||. Documents the layer-0 dominance pattern that drives the headline aggregate Γ on these checkpoints. - results/vanilla_dfa_early_ckpts/per_layer_cos_3seed.json: machine- readable dump of all 6 measurements for future audit. - §7 compressed (~30 words trimmed across the closing paragraph) and Figure 3 width 0.92 → 0.82 to keep main content at exactly 9 pages after the appendix addition. Verified: 9 pages main + refs on p10, 18 total, 0 overfull boxes. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'results')
-rw-r--r--results/vanilla_dfa_early_ckpts/per_layer_cos_3seed.json98
1 files changed, 98 insertions, 0 deletions
diff --git a/results/vanilla_dfa_early_ckpts/per_layer_cos_3seed.json b/results/vanilla_dfa_early_ckpts/per_layer_cos_3seed.json
new file mode 100644
index 0000000..b1c9de6
--- /dev/null
+++ b/results/vanilla_dfa_early_ckpts/per_layer_cos_3seed.json
@@ -0,0 +1,98 @@
+{
+ "s42_ep1": {
+ "per_layer_cos": [
+ 0.4208017587661743,
+ 0.004838745109736919,
+ -0.027907393872737885,
+ -0.038808517158031464,
+ -0.03807452693581581
+ ],
+ "per_layer_g_norm_median": [
+ 1.2788983667633147e-06,
+ 6.714879532410123e-07,
+ 6.794414844080165e-07,
+ 6.840860464762955e-07,
+ 6.860727808088996e-07
+ ]
+ },
+ "s42_ep2": {
+ "per_layer_cos": [
+ 0.4369885325431824,
+ -0.001831148169003427,
+ -0.039548110216856,
+ -0.05499383062124252,
+ -0.05395658314228058
+ ],
+ "per_layer_g_norm_median": [
+ 5.726975587094785e-07,
+ 1.5392966190574953e-07,
+ 1.5485885285215772e-07,
+ 1.5658912388971657e-07,
+ 1.576423045435149e-07
+ ]
+ },
+ "s123_ep1": {
+ "per_layer_cos": [
+ 0.43564510345458984,
+ 0.008119785226881504,
+ -0.032616909593343735,
+ 0.015984557569026947,
+ 0.0165080688893795
+ ],
+ "per_layer_g_norm_median": [
+ 1.1976044334005564e-06,
+ 6.545930091306218e-07,
+ 6.567059358530969e-07,
+ 6.61169508475723e-07,
+ 6.618395786972542e-07
+ ]
+ },
+ "s123_ep2": {
+ "per_layer_cos": [
+ 0.4596974849700928,
+ 0.005399191286414862,
+ -0.03668719530105591,
+ 0.0029763614293187857,
+ 0.0030912011861801147
+ ],
+ "per_layer_g_norm_median": [
+ 5.662583362209261e-07,
+ 1.351014162764841e-07,
+ 1.350312288650457e-07,
+ 1.36037257902899e-07,
+ 1.3582508984200103e-07
+ ]
+ },
+ "s456_ep1": {
+ "per_layer_cos": [
+ 0.4175308644771576,
+ 0.010558882728219032,
+ -0.026187893003225327,
+ 0.007104482501745224,
+ 0.006094767712056637
+ ],
+ "per_layer_g_norm_median": [
+ 1.0160714509765967e-06,
+ 3.9226171111295116e-07,
+ 3.8446077610387874e-07,
+ 3.8279964087450935e-07,
+ 3.864832649469463e-07
+ ]
+ },
+ "s456_ep2": {
+ "per_layer_cos": [
+ 0.40920183062553406,
+ 0.002915931399911642,
+ -0.038979340344667435,
+ 0.0008528914768248796,
+ 6.853311788290739e-06
+ ],
+ "per_layer_g_norm_median": [
+ 4.5268734538694844e-07,
+ 8.855825228692993e-08,
+ 8.533425699397412e-08,
+ 8.582557597947016e-08,
+ 8.653171335026855e-08
+ ]
+ }
+} \ No newline at end of file