Symbol C
C is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
Read this term in its guide →Published equation contexts
Why this formula appears here
The defence against this is a control condition run alongside the target one, not after it: intervene identically on a component set ' matched to the target set in size, depth and baseline activation statistics, but which the hypothesis explicitly predicts should have no effect, and compare
Read the representative guide
How to interpret it
Read this expression with the definitions, units, and assumptions supplied by the article.
Research cited beside this formula
- [3] Towards Best Practices of Activation Patching in Language Models: Metrics and Methods ↗
- [4] Causal Scrubbing: A Method for Rigorously Testing Interpretability Hypotheses ↗
- [5] Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching ↗
- [6] Towards Automated Circuit Discovery for Mechanistic Interpretability ↗
Published contexts (2)
A symbol can carry a different meaning in another article. Each occurrence keeps its own guide and term definitions.
Equation 8 · AI Research
Running an Interpretability Investigation That Holds Up
This mathematical expression combines the displayed quantities; its precise role follows from the surrounding article text.
The defence against this is a control condition run alongside the target one, not after it: intervene identically on a component set ' matched to the target set in size, depth and baseline activation statistics, but which the hypothesis explicitly predicts should have no effect, and compare
Equation guide → · Article →Equation 15 · AI Research
Running an Interpretability Investigation That Holds Up
This mathematical expression combines the displayed quantities; its precise role follows from the surrounding article text.
A patching experiment produces two different kinds of statement, and the write-up has to keep them visibly separate. The first is a measurement: intervening on component set moved metric m by some amount, with some variance across prompts and random seeds, and the matched control ' moved it by some smaller amount. That is data. The second is an interpretation layered on top of it: that the component “represents,” “detects,” or “computes” some human concept. The measurement is usually solid. The interpretation is usually the part doing more work than the evidence supports, and it is the part press coverage and even conference talks tend to keep while dropping every…
Equation guide → · Article →