INDEX

Explanations

references to statistical coefficients and their related contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vica

-0.53

 ويكيپيديا

-0.53

AccessorTable

-0.53

yntaxException

-0.52

 Drapeau

-0.52

 ExecuteAsync

-0.51

 distinguishing

-0.50

 carica

-0.49

tro

-0.48

avadoc

-0.48

POSITIVE LOGITS

 Coefficient

1.10

 coefficients

1.09

 coefficient

1.09

coefficient

1.07

 Coefficients

1.05

 BUREAU

1.05

 Bureau

1.00

Coefficient

0.98

coefficients

0.90

Bureau

0.89

Activations Density 0.049%

references to statistical coefficients and their related contexts

No Comments

No Known Activations