Equation 1 · Part 4 · Probing, Sparse Autoencoders, Patching, and Steering: The Main Interpretability Methods, Compared
Symbol w^top
What this part means
op is one of the signed contributions combined to compute the quantity on the left.
Its job in the formula
op is one of the signed contributions combined to compute the quantity on the left.
Full expression→Symbol w^top→Article meaning
The passage around this formula
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.
Learn the underlying idea
An exponent tells how a base is used in multiplication. In x³, x is the base and 3 is the exponent: x³ = x × x × x.
Open the illustrated exponents: repeated multiplication and powers 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.