Equation 5 · Part 2 · Probing, Sparse Autoencoders, Patching, and Steering: The Main Interpretability Methods, Compared
Symbol b
What this part means
the probe’s own parameters, trained on labelled examples the network never saw during its own training.
Its job in the formula
b 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 b→Article meaning
Where the article explains it
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.
The passage around this formula
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.
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
- [1] Understanding Intermediate Layers Using Linear Classifier Probes ↗
- [2] What You Can Cram into a Single Vector: Probing Sentence Embeddings for Linguistic Properties ↗
- [3] Designing and Interpreting Probes with Control Tasks ↗
- [4] Probing Classifiers: Promises, Shortcomings, and Advances ↗
These citations provide research context; check each source for the exact claim it supports.