Four best contrastive prompt pairs outperform full 16-pair average steering vector for type hint suppression

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

• Steering vector constructed from all 16 contrastive pairs outperforms most single-pair vectors; best 4-pair vector outperforms full 16-pair vectorfinding0.881
  Demonstrates averaging multiple prompt pairs reduces noise; optimal subset selection further improves performance.
• Steering at 6 layers (strength 0.6 each, total 3.6) outperforms single-layer steering at equivalent total strength for type hint suppressionfinding0.822
  Demonstrates distributed steering is more effective and less accuracy-damaging than concentrated steering.
• 24 Gaussian noise vectors (matched mean/variance/ℓ2 norm) do not decrease type hint rate nearly as much as deployment steering vectorfinding0.814
  Robustness check ruling out that any perturbation would decrease type hint rate due to brittleness.
• Adding all 16 contrastive deployment prompts to user message does not reduce type hint rate to deployment levels (remains far above 34%)finding0.791
  Demonstrates steering is not equivalent to prompting with the contrastive prompts.
• The combined CV-SAE+Prompt configuration achieves the best overall performance, confirming that contrastively trained latent vectors enhance persona control while preserving dialogue coherenceclaim0.768
  Central performance claim of the paper summarizing experimental results
• Steering vectors discover effective triggers such as 'However' and 'Otherwise', consistent with prior reported reflection datasetsfinding0.767
  Validates that steering vectors capture reflection semantics by finding tokens reported in related work.
• Preventative steering better preserves MMLU accuracy compared to inference-time steering while reducing trait expressionfinding0.764
  Key advantage of preventative over post-hoc steering: lower side-effect cost on general capabilities
• Response-average token extraction yields stronger steering effectiveness than prompt-last or prompt-average extraction positionsfinding0.763
  Justifies the choice of response tokens for persona vector extraction in the pipeline