Equation 11 · How Mechanistic Interpretability Research Is Actually Done
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
subscript
The lower label selects a particular version, component, or indexed member of the quantity. For example, x₀ and xₜ can be values at different positions.
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 penalty has a known cost: it does not directly control how many dictionary elements fire, only how much their combined magnitude is discouraged, and it systematically shrinks the elements that do fire toward zero, biasing the reconstruction. Two later refinements address this more directly. Gao and colleagues introduced k -sparse encoding, which drops the tunable penalty in favour of a fixed sparsity budget enforced structurally,
Sources cited in the article section
- [6] Sparse Autoencoders Find Highly Interpretable Features in Language Models ↗
- [7] Towards Monosemanticity: Decomposing Language Models With Dictionary Learning ↗
- [8] Scaling and evaluating sparse autoencoders ↗
- [9] Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders ↗
- [10] Interpreting Attention Layer Outputs with Sparse Autoencoders ↗
These citations give research context. Read each source to check which claims it supports.
Return to How Mechanistic Interpretability Research Is Actually Done