Equation 18 · Part 1 · Probing, Sparse Autoencoders, Patching, and Steering: The Main Interpretability Methods, Compared

Symbol m_clean

m_{\text{clean}}

m_{\text{clean}}

What this part means

a chosen behavioural metric measured on the clean and corrupted runs.

Its job in the formula

$m_c$ lean is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.

Full expressionSymbol m_cleanArticle 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 subscript is a label attached below a symbol. It often selects a time step, component, category, or member of a sequence.

Open the illustrated subscripts: which member of a family? 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.