{
  "model": "google/gemma-2-2b-it",
  "study_checkpoint_dir": "/common/users/vp752/iconoclast_ilabs/checkpoints/gemma2-2b-seq",
  "base_metrics": {
    "refusals": 20,
    "overrefusals": 4,
    "harmful_marker_hits": 51,
    "harmful_compliance_score": 0.46687499999999993,
    "objective_regime": "refusal_reduction"
  },
  "pareto_trials": [
    {
      "index": 33,
      "refusals": 1,
      "overrefusals": 0,
      "harmful_marker_hits": 2,
      "harmful_compliance_score": 0.6854166666666666,
      "objective_regime": "refusal_reduction",
      "merge_penalty": 0.0,
      "kl_divergence": 0.18489933013916016,
      "direction_method": "mean",
      "direction_scope": "global",
      "direction_index": 17.39644304578948,
      "direction_blend": 0.518857148550465,
      "parameters": {
        "attn.o_proj": {
          "max_weight": 1.3097319950489419,
          "max_weight_position": 15.170423455317254,
          "min_weight": 0.4048379564530448,
          "min_weight_distance": 12.325696697693427
        },
        "mlp.down_proj": {
          "max_weight": 1.8381079612498168,
          "max_weight_position": 22.13528928970058,
          "min_weight": 1.7320857100777993,
          "min_weight_distance": 13.690846822591785
        }
      },
      "harmful_axis_metrics": {}
    },
    {
      "index": 30,
      "refusals": 2,
      "overrefusals": 0,
      "harmful_marker_hits": 2,
      "harmful_compliance_score": 0.6502083333333335,
      "objective_regime": "refusal_reduction",
      "merge_penalty": 0.0,
      "kl_divergence": 0.18217073380947113,
      "direction_method": "mean",
      "direction_scope": "global",
      "direction_index": 16.451937007645025,
      "direction_blend": 0.4440618960208035,
      "parameters": {
        "attn.o_proj": {
          "max_weight": 1.8057060898159651,
          "max_weight_position": 19.984434904037112,
          "min_weight": 0.44650454405469425,
          "min_weight_distance": 14.620100821848816
        },
        "mlp.down_proj": {
          "max_weight": 1.7127451564806415,
          "max_weight_position": 20.954344002491393,
          "min_weight": 1.526231827300012,
          "min_weight_distance": 13.25096787421839
        }
      },
      "harmful_axis_metrics": {}
    },
    {
      "index": 26,
      "refusals": 3,
      "overrefusals": 0,
      "harmful_marker_hits": 3,
      "harmful_compliance_score": 0.6982291666666667,
      "objective_regime": "refusal_reduction",
      "merge_penalty": 0.0,
      "kl_divergence": 0.14583510160446167,
      "direction_method": "variance",
      "direction_scope": "global",
      "direction_index": 15.03370265340769,
      "direction_blend": 0.09524297173841478,
      "parameters": {
        "attn.o_proj": {
          "max_weight": 1.8738445289261785,
          "max_weight_position": 18.952393144953646,
          "min_weight": 0.007193109525560186,
          "min_weight_distance": 13.737333198768454
        },
        "mlp.down_proj": {
          "max_weight": 1.578589273226791,
          "max_weight_position": 10.646710843869595,
          "min_weight": 1.540999399011012,
          "min_weight_distance": 11.707974920105963
        }
      },
      "harmful_axis_metrics": {}
    }
  ]
}