INDEX

Explanations

the word "bon" and its variations in different contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 vulgaires

-0.63

 виправивши

-0.60

ństwa

-0.57

ToBounds

-0.53

ństwo

-0.53

tonsoft

-0.53

jár

-0.51

currentColor

-0.51

labelledby

-0.50

XtraReports

-0.49

POSITIVE LOGITS

Bon

0.88

Bon

0.87

bon

0.85

BON

0.77

BON

0.75

bon

0.73

 Bons

0.70

Bons

0.69

bons

0.66

bonne

0.66

Activations Density 0.080%

the word "bon" and its variations in different contexts

No Comments

No Known Activations