Symbol hat y
hat y is part of the quantity the equation computes from the expression on the right.
Read this term in its guide →Published equation contexts
Why this formula appears here
Formally, a probe is a function fitted independently of the network under study: . where is the frozen activation the network produces at layer for input x , and w, b are the probe’s own parameters, trained on labelled examples the network never saw during its own training. Nothing in that objective touches the network’s weights or its downstream computation. A probe reports only whether some linear function of this one activation predicts the label well.
Read the representative guide
Symbol x
x is an argument of the function-like quantity on the left; its role is set by that function’s stated inputs.
Read this term in its guide →Symbol σ
σ is one of the signed contributions combined to compute the quantity on the left.
Read this term in its guide →Symbol w^top
op is one of the signed contributions combined to compute the quantity on the left.
Read this term in its guide →Symbol h_ell
the frozen activation the network produces at layer for input x , and w.
Read this term in its guide →Symbol b
the probe’s own parameters, trained on labelled examples the network never saw during its own training.
Read this term in its guide →How to interpret it
Read it with the definitions, units, and assumptions supplied by the article.
Research cited beside this formula
Published contexts (1)
A symbol can carry a different meaning in another article. Each occurrence keeps its own guide and term definitions.
Equation 1 · AI Research
Probing, Sparse Autoencoders, Patching, and Steering: The Main Interpretability Methods, Compared
This equation states an equality: the expressions on both sides have the same value under the article’s assumptions.
Formally, a probe is a function fitted independently of the network under study: . where is the frozen activation the network produces at layer for input x , and w, b are the probe’s own parameters, trained on labelled examples the network never saw during its own training. Nothing in that objective touches the network’s weights or its downstream computation. A probe reports only whether some linear function of this one activation predicts the label well.
Meanings in this article
- : the frozen activation the network produces at layer for input x , and w.
- : the probe’s own parameters, trained on labelled examples the network never saw during its own training.