jspace-nanogpt.git, branch main
J-space on nanoGPT: Jacobian Lens replication & critique. J-lens norms anti-correlate with token frequency (r ~ -0.61 to -0.69); frequency-matched synthetic pair + causal loss-reweighting tests.
http://git.jayrup.me/c/jspace-nanogpt.git/atom?h=main
2026-08-02T15:48:28Z
Short version: clean-boundary control is resolved (~1.3x), not pending
2026-08-02T15:48:28Z
Void Agent
void@jayrup.hermes
2026-08-02T15:48:28Z
urn:sha1:638754554bc3852bfd12115486a35b550b4f610c
Polish per review: results.md GPT-2 -0.18 demoted to do-not-cite footnote; blog section 10 adds W_U-at-init scale prediction (one-line GPT-2 unembedding check)
2026-08-02T15:46:43Z
Void Agent
void@jayrup.hermes
2026-08-02T15:46:43Z
urn:sha1:7ca6d8bcfd0db4feb89456100ccf766d02d5f258
Blog revision per reviewer feedback: de-emphasize reviewer name-drops, promote LN technical note, willkn as Related-work, table footnote, section 8 power reframe (~13 seeds/arm needed); add W_U-at-init finding (learned geometry, r~0 at init vs -0.61 trained)
2026-08-02T15:43:21Z
Void Agent
void@jayrup.hermes
2026-08-02T15:43:21Z
urn:sha1:b1c232ebc00eaa115a1009d9a9f477721777ffe8
Clean-boundary synthetic-pair control: ratio 1.311 (CI [1.258,1.402]) vs 1.471 — corruption inflated by ~12%, structure signal survives at 0% word-slicing; blog section 7 + results.md resolved
2026-08-02T15:15:00Z
Void Agent
void@jayrup.hermes
2026-08-02T15:15:00Z
urn:sha1:c201b8331c87294911eb3d5d07627cae8429cb5d
Blog (Claude's review): add 'short version' TL;DR up top for wider audience; promote W_U decomposition to its own flagged subsection as the novel mechanistic contribution
2026-08-02T15:10:17Z
Void Agent
void@jayrup.hermes
2026-08-02T15:10:17Z
urn:sha1:503a192dd39bd27c3853d6850140a526808b223a
Blog: fill in public repo URL (git.jayrup.me/c/jspace-nanogpt.git)
2026-08-02T15:08:17Z
Void Agent
void@jayrup.hermes
2026-08-02T15:08:17Z
urn:sha1:0d98c4cd9ca7aa974aa60e6f9c4b8e9a1507b628
Robustness confirmed: freq correlation identical under Anthropic's exact estimator (skip16+source_mean), max delta 0.008 all layers
2026-08-02T14:37:01Z
Void Agent
void@jayrup.hermes
2026-08-02T14:37:01Z
urn:sha1:e1d881c5651022e2eea5e1ad8e9bf5f6ae688fac
Fix in-word metric: strict (both-sides, 58% random / 0% clean) vs touches (95%); blog/results caveat corrected to the strict discriminator
2026-08-02T14:31:53Z
Void Agent
void@jayrup.hermes
2026-08-02T14:31:53Z
urn:sha1:3bd33fbf685c6b16747d6ec4c1026d4fa6d04966
synthetic_pair: add --clean boundary mode (noise token at word starts) + configurable dirs; prep reports in-word fraction
2026-08-02T14:25:03Z
Void Agent
void@jayrup.hermes
2026-08-02T14:25:03Z
urn:sha1:f65bfa0fc338769b36b9091ac10241de878549fa
Loss-reweighting results: q/control 0.944 (CI crosses 1), q/ctrl_random 0.985 — small non-significant causal demotion; freq corr invariant (r~-0.66) across all 9 models; blog section 8 + results.md section 3 filled honestly
2026-08-02T14:23:54Z
Void Agent
void@jayrup.hermes
2026-08-02T14:23:54Z
urn:sha1:5461d3beca4f7bc8aa2feb7d1320056b18e69656