method
active
method:l2zi-injection

L2ZI Injection

Probe-based injection using L2-regularized logistic regressor with zero intercept on h_b activations

Neighborhood — ranked by edge-count

Methods (2)

method
  • L2LI Injection
    related_to
    Probe-based injection using L2-regularized logistic regressor with learned intercept on h_b activations
  • L1ZI Injection
    related_to
    Probe-based injection using L1-regularized logistic regressor with zero intercept on h_b activations

Related by similarity (5)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • L1LI Injectionmethod0.760
    Probe-based injection using L1-regularized logistic regressor with learned intercept on h_b activations
  • Injection Stridemethod0.692
    Parameter controlling how often an injection is applied during completion; s=1 injects on every activation, achieving strongest steering
  • MDS Injectionmethod0.680
    Mean-difference vectors derived from self-statement activations (h_s); best-performing injection method in open-ended generation
  • MDB Injectionmethod0.673
    Mean-difference vectors derived from Yes/No binary-prefill activations (h_b)
  • Concept Injectionconcept0.654
    Technique of injecting activation patterns associated with specific concepts into a model's internal states to test whether self-reports reflect ground truth.