Equation 21 · Part 1 · Probing, Sparse Autoencoders, Patching, and Steering: The Main Interpretability Methods, Compared

Symbol C

\mathcal C

C

What this part means

copied from one run into the other.

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 expressionSymbol CArticle meaning

Where the article explains it

where $m_{\text{clean}}$ and $m_{\text{corrupt}}$ are a chosen behavioural metric measured on the clean and corrupted runs, and $m_{\text{patch}}(\mathcal C)$ is that same metric after the activations of component set $\mathcal C$ are copied from one run into the other.

The passage around this formula

where $m_{\text{clean}}$ and $m_{\text{corrupt}}$ are a chosen behavioural metric measured on the clean and corrupted runs, and $m_{\text{patch}}(\mathcal C)$ is that same metric after the activations of component set $\mathcal C$ are copied from one run into the other. A score near one means patching $\mathcal C$ alone restores nearly all of the clean behaviour; a score near zero means it restores almost none.

Read this part in the article →

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 article section

These citations provide research context; check each source for the exact claim it supports.