method
active
method:zero-ablationZero Ablation
Intervention type that sets activations to zero, used for interpretability analysis
Neighborhood — ranked by edge-count
Methods (2)
method
- Zero ablation of latentsrelated_toStronger test of concept isolation than steering.
- Zero Ablation Studyrelated_toSequential zeroing out of high-contribution heads to verify their functional specialization for persona control
Artifacts (1)
artifact
- pyvene open-source Python libraryimplementsThe main artifact introduced in the paper: an open-source PyPI library for customizable interventions on PyTorch models
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Ablates top-k PCs of character-count means vs random subspace.
- Clamping a feature's value to zero to measure its causal effect on model output.
- Robustness check ablating over five steering coefficient values to test whether SP/AS inversion is an artifact of steering strength
- Intervention method that removes a direction from residual stream activations to disrupt corresponding behavior
- Classical techniques to interrogate regulative capacity of embryos and neural crest by tissue removal or transplantation.
- Technique used in VPD to enforce mechanistic faithfulness of parameter decompositions.
- Projecting out top-k J-lens directions to test necessity.
- Justifies SCR/TPP.