Equation 25 · Part 12 · Probing, Sparse Autoencoders, Patching, and Steering: The Main Interpretability Methods, Compared
subscript
subscript
What this part means
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.
Its job in the formula
A subscript distinguishes a version, component, step, or member of a quantity. It does not automatically mean multiplication.
Full expression→subscript→Article meaning
The passage around this formula
The construction is a mean-difference direction, added back into the residual stream with a tunable strength at inference time: . where P and N index matched positive and negative examples of the target behaviour, is the residual-stream activation at layer , and is a coefficient the operator sets by hand. Nothing in this construction requires understanding why the network represents the concept along this direction, only that adding it produces the intended behavioural shift.
Learn the underlying idea
A subscript is a label attached below a symbol. It often selects a time step, component, category, or member of a sequence.
Open the illustrated subscripts: which member of a family? guide →
Sources cited in the article section
- [12] Representation Engineering: A Top-Down Approach to AI Transparency ↗
- [13] Steering Language Models With Activation Engineering ↗
- [14] Steering Llama 2 via Contrastive Activation Addition ↗
- [15] Analyzing the Generalization and Reliability of Steering Vectors ↗
These citations provide research context; check each source for the exact claim it supports.