spb/modelmap Public License

1{2  "map_id": "atlas/qwen3-0.6b-4bit/interventions/v1",3  "map_type": "interventions",4  "model_id": "mlx-community/Qwen3-0.6B-4bit",5  "model_hash": "392e8d466d56100ada00eb82031fb854297fc9e389b7d303eba3af114e87bce2",6  "quantization": "q4 (mlx)",7  "commit": "f7c298d2859ed43654d388618b7274266e7e562b",8  "config": "results/expC_causal_verification/20260812T071954Z/results.json",9  "created": "2026-08-12",10  "hardware_manifest": {11    "author": "Simon-Pierre Boucher",12    "contact": "contact@spboucher.ai",13    "website": "https://modelmap.io",14    "chip": {15      "brand": "Apple M5 Max",16      "cores_total": 18,17      "cores_performance": 6,18      "cores_efficiency": 1219    },20    "memory": {21      "unified_gb": 48.0,22      "pagesize": 1638423    },24    "os": {25      "system": "Darwin",26      "version": "27.0",27      "arch": "arm64"28    },29    "software": {30      "python": "3.14.4",31      "numpy": "2.5.2",32      "mlx": "0.32.0",33      "torch": "2.13.0",34      "safetensors": "0.8.0"35    }36  },37  "confidence_level": 2,38  "regenerate_command": ".venv/bin/python experiments/micro/expC_causal_verification/implementation/benchmark_v4.py && .venv/bin/python experiments/micro/expC_causal_verification/implementation/make_interventions_mapcard.py",39  "seeds": [40    780,41    "Ahalf1",42    "Ahalf2",43    "bootA",44    "Bhalf1",45    "Bhalf2",46    "bootB"47  ],48  "prompt_sets": [49    "agreement_A halves (direction est.)",50    "agreement_B halves (direction est.)",51    "fresh held-out minimal-pair bank (8 unseen locations)"52  ],53  "controls": [54    "random-direction erasure per layer (3 dirs, netted out)",55    "six-source replication with pre-registered bar (runs #3-#4)",56    "late band excluded as estimator-unstable (run #3 refusal)"57  ],58  "methods_in_agreement": [59    "difference-in-means probing (direction exists, decodable)",60    "direction erasure (causally load-bearing)"61  ],62  "interventions": [63    "rank-1 direction erasure at each layer's output, all positions"64  ],65  "replication_rate": 0.7254,66  "per_dataset_agreement": null,67  "ablation_schemes": [],68  "featurizer_class": "linear (difference-in-means direction)",69  "intervention_protocol": "erase h' = h − ⟨h−μ,u⟩u at layer ℓ; logit-margin metric; random-direction null netted out; BAND granularity",70  "negative_result": false,71  "notes": "Level 2, NOT 3: the two agreeing methods share the diff-of-means estimator; activation-addition steering is the registered Level-3 path. This entry exists because run #3's per-layer version was REFUSED by the gate — the band is the granularity that replicates. Anti-correlates with probes/v2 layer ranking (survival ledger 0/2): decodability peaks ≠ causal joints.",72  "author": "Simon-Pierre Boucher",73  "contact": "contact@spboucher.ai",74  "website": "https://modelmap.io",75  "schema_version": "0.1"76}77