INDEX

Explanations

numeric values or parameters representing quantities or counts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Désolé

-0.55

رشف

-0.53

seamnă

-0.53

__':

-0.52

 geïsole

-0.52

__':

-0.52

if

-0.51

 sportivo

-0.50

 toepassing

-0.50

rrbracket

-0.49

POSITIVE LOGITS

GEBURTSDATUM

0.95

 للاسماء

0.75

 وتسجيلات

0.66

verwijspagina

0.59

 怎样

0.58

 name

0.58

","","

0.57

Eksteraj

0.56

__(/*!

0.55

fällig

0.55

Activations Density 0.051%

numeric values or parameters representing quantities or counts

No Comments

No Known Activations