wassnameandClaudypoo 9149e8c1d1 demo: quantitative readouts -- rubric coherence-sweep + reference lens-rank ...

Two readouts added to the steering demo, both fresh-eyes signed off:

- rubric_score + coherence_sweep + plot_sweep: the model thinks then answers a
  forced {"ans": N} slot; we read the logprob-weighted expected digit and its
  pmass coherence. coherence_sweep walks C outward from 0 both ways, stopping a
  side when the answer slot goes incoherent (pmass<floor), averaging n_samples
  seeded traces (BMA) so the dose-response isn't single-sample noise. plot_sweep
  colours points by pmass with the ramp anchored to [floor-0.15,1] (0-1 washed
  every point one colour) and a red cutoff line. show_steer gains a `rubric` arg.

- lens_slice_ranks + plot_lens_slice: render jlens's own compute_slice output
  (the reference's auto token selection over the full layer grid + full-vocab
  ranks + J=I model row) as a table + rank-vs-depth plot, rather than reimplement
  it. Rank, not raw lens-logit, is comparable across layers. CJK-first font so
  multilingual tokens (e.g. the auto-surfaced 巴黎) render in the legend.

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

2026-07-11 11:03:13 +08:00

..

__init__.py

demo: print raw generation (skip_special_tokens=False), drop split_think

2026-07-10 20:17:32 +08:00

applies.py

persona refinements: soft-cotangent vector, pinv tangent transport, topk word-like mask

2026-07-11 08:05:01 +08:00

demo.py

demo: quantitative readouts -- rubric coherence-sweep + reference lens-rank

2026-07-11 11:03:13 +08:00

jacobian.py

persona refinements: soft-cotangent vector, pinv tangent transport, topk word-like mask

2026-07-11 08:05:01 +08:00

vjp.py

wip

2026-07-10 14:36:55 +08:00