← All symbols

Symbol in context

λ\lambda

This entry links every published equation using this exact notation. Its meaning may change between equations.

Meanings in context

Used in 68 equations

x^=Wdf(x)+bd,f(x)=JumpReLUθ(Wex+be),L(x)=∥x−x^∥22+λ∥f(x)∥0.\hat x = W_d f(x) + b_d, \qquad f(x) = \mathrm{JumpReLU}_\theta\big(W_e x + b_e\big), \qquad \mathcal L(x) = \lVert x - \hat x \rVert_2^2 + \lambda \lVert f(x) \rVert_0.

Probing, Sparse Autoencoders, Patching, and Steering: The Main Interpretability Methods, Compared · Equation 9

This equation states an equality: the expressions on both sides have the same value under the article’s assumptions.

Equation guide → · This term → · Article →
LSAE(a)=∥a−a^∥22+λ∥z∥1,a^=Wdec z+bdec,z=ReLU ⁣(Wenc(a−bdec)+benc).\mathcal{L}_{\mathrm{SAE}}(a) = \lVert a - \hat a \rVert_2^2 + \lambda \lVert z \rVert_1, \qquad \hat a = W_{\mathrm{dec}}\, z + b_{\mathrm{dec}}, \qquad z = \mathrm{ReLU}\!\left(W_{\mathrm{enc}}(a - b_{\mathrm{dec}}) + b_{\mathrm{enc}}\right).

How Mechanistic Interpretability Research Is Actually Done · Equation 9

This equation states an equality: the expressions on both sides have the same value under the article’s assumptions.

Equation guide → · This term → · Article →