Equation 24 · Part 1 · Probing, Sparse Autoencoders, Patching, and Steering: The Main Interpretability Methods, Compared
Symbol C
What this part means
sufficient to restore the behaviour.
Its job in the formula
C is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
Full expression→Symbol C→Article meaning
Where the article explains it
Patching in one direction — copying clean activations into a corrupted run, “denoising” — tests whether is sufficient to restore the behaviour; patching in the other direction — copying corrupted activations into a clean run, “noising” — tests whether is necessary to sustain it, and the two are not mirror images of the same fact about the network.
The passage around this formula
…clearest documented source on how easily the result changes under choices that are rarely reported in full. Patching in one direction — copying clean activations into a corrupted run, “denoising” — tests whether is sufficient to restore the behaviour; patching in the other direction — copying corrupted activations into a clean run, “noising” — tests whether is necessary to sustain it, and the two are not mirror images of the same fact about the network. The choice of corruption itself, whether…
Learn the underlying idea
A variable is a named place for a value. Its letter is a local label: x can mean position in one formula and a data point in another.
Open the illustrated variables: a letter stands for a value guide →
See this notation across published equations →
Sources cited in the surrounding passage
These citations provide research context; check each source for the exact claim it supports.