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/data/atlas-index.json · clear filter

  1. expC run #4: BAND claim passes — first Level-2 atlas entry (causal map)
    …
    Early-band (2-15) mean specific damage +3.23..+3.35 across six fresh
direction sources (min +3.228 vs pre-registered bar 2.5; spread 0.12) on
a fresh behavioral bank (baseline +4.45). Late band unstable, no claim.
Published atlas/qwen3-0.6b-4bit/interventions/v1 (Level 2): a single
diff-of-means agreement direction, erased at any early-band layer,
removes ~73-75% of grammatical preference. The gate that refused run #3's
per-layer map passed the band version. Band map leads the home page.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
    Simon-Pierre Boucher committed 4 h ago (Aug 12, 2026) · 1 file changed +11
  2. expA run #2: first positive maps (agreement, arith_valid) + real noise floor
    …
    - v2 promptsets: structure-borne, token-balanced (overlap certificates);
  capture_pooled returns mean+last-token reps in one pass
- Strict twin gate falsified again (word_order twin acc 0.96 — subword
  statistics); gate retired, differential (real-twin) is the map
- agreement: 25/28 signal layers (max dSel +0.379); arith_valid: real
  0.86/0.90 vs twin 0.56, strongest last-token; word_order null-dominated
- First real noise floor: top-5 replication ~0.54 off ceiling; dataset
  shift > seed SD on only 3-8/28 layers (registered 1/3 not met)
- atlas probes/v2 published (Level 1, per-property verdicts); site charts
  generalized to any probes entry; home leads with agreement map

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
    Simon-Pierre Boucher committed 4 h ago (Aug 12, 2026) · 1 file changed +11
  3. expA run #1: validity gate FAILED — first atlas entry is a negative result
    …
    - src/modelmap/capture: MLX Tap layer + random-init architecture twin
- promptsets v1 (6x240, sha256 manifest) — now the positive-control corpus
- Result: ceiling everywhere (acc 1.000); twin ALSO at 1.00 on all 28
  layers (max sel 0.56-0.88 vs registered 0.05 gate) — probe map reads
  tokenizer+architecture prior, zero trained-model signal. Shuffled-label
  control would not have caught it; only the twin null did.
- Published atlas/qwen3-0.6b-4bit/probes/v1 (negative_result=true,
  Level 1, replication 1.00) via publish.py gate
- Doctrine: probe maps only as REAL-TWIN differentials from now on

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
    Simon-Pierre Boucher committed 5 h ago (Aug 12, 2026) · 1 file changed +13 −1
  4. Phase 5 substrate + expH run #1: first measured result
    …
    - mapcard v0 schema + publish gate (G23), stats core (bootstrap/FDR/
  replication), probe harness with built-in shuffled-label controls
  (unit test caught a fancy-indexing shuffle bug pre-science)
- expH hypothesis registered before run; run #1 on M5 Max 48GB:
  (A) mmap 3.2-10.8x zarr on random-batch reads (confirmed >=2x bar);
  (B) MLX capture nearly free (1.02x), torch-MPS retain 1.22x (confirmed)
- expA hypothesis registered (dataset-variance > seed-variance)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
    Simon-Pierre Boucher committed 6 h ago (Aug 12, 2026) · 1 file changed +6