Equation 7 · Probing, Sparse Autoencoders, Patching, and Steering: The Main Interpretability Methods, Compared
What does this equation mean?
Read the formula alongside the article passage below. Each part has a deeper page with its role in the equation, the supporting passage and nearby citations.
This mathematical expression combines the displayed quantities; its precise role follows from the surrounding article text. Read the equation part by part below; each part has a contextual explanation and a link to its mathematical background.
Read it piece by piece
Symbol x
x is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
How to interpret it
Read this expression with the definitions, units, and assumptions supplied by the article.
What the article says around this equation
The formal objective has evolved since the earliest versions, and the direction of that evolution is itself informative. A dictionary decoder reconstructs the activation x from a sparse code f(x) :
Sources cited in the article section
- [5] Toy Models of Superposition ↗
- [6] Towards Monosemanticity: Decomposing Language Models With Dictionary Learning ↗
- [7] Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders ↗
- [8] A Is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders ↗
These citations give research context. Read each source to check which claims it supports.