SPB Git

spb/modelmap Public License

Internal cartography of local LLMs on Apple Silicon — registered, gated, negative-first. Public atlas at modelmap.io.

🔗 https://modelmap.io
interpretabilityllmapple-siliconmlxreproducibility
Python 66.3% JavaScript 24.5% CSS 8.1% Shell 0.7%

History of site/lib/charts.js · clear filter

  1. expC run #6: L12 handle fails replication — Level 3 abandoned (as registered)
    …
    Only 1/4 fresh sources monotone (positive dose arm unstable); specificity
failed to replicate (random |delta| 3.36 vs bound 1.14 — run #5's 0.45 was
3-draw sampling luck). Halving held 4/4: necessary but not a reliable
additive handle. interventions/v1 (Level 2) stands as the final causal
claim. Gate record: refuse -> pass(L2) -> refuse -> refuse. Methodology
rule adopted: specificity controls need >=10 random draws + percentile
bound. Charts: x-axis customization for dose-response figures.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
    Simon-Pierre Boucher committed 4 h ago (Aug 12, 2026) · 1 file changed +6 −4
  2. expC run #3: publication gate refused the causal profile (as designed)
    …
    Replication failed: mean pairwise rho 0.495 (<0.7), band claim fails on
2/5 direction sources; make_interventions_mapcard.py exits 1 and the
atlas stays at two entries. The refusal decomposes the object: early band
(2-15) replicates tightly (+2.98..+3.34 of +4.24), late band (20-27) is
estimator noise (-0.44..+2.77) -- retroactively explaining run #2's
anti-correlation. Run #4 pre-registers the narrower BAND claim.
Charts: interventions profile builder + dynamic y-axis (renders when a
map passes the gate).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
    Simon-Pierre Boucher committed 4 h ago (Aug 12, 2026) · 1 file changed +9 −2
  3. Site: server-rendered SVG result maps (dataviz-validated palette)
    …
    - lib/charts.js: layer-profile lines, small-multiple bar panels, grouped
  bars — palette validated with the six-checks script (violet/orange PASS;
  aqua carries mandatory direct labels; twin = dashed neutral reference)
- expA probe map (trained A/B vs random-init twin) on home, experiment
  page and atlas entry; expH warm/cold storage panels + capture-overhead
  bars on home and experiment page; per-mark hover tooltips, legends

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
    Simon-Pierre Boucher committed 5 h ago (Aug 12, 2026) · 1 file changed +176