INDEX

Explanations

numerical values and measurements within the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Datuak

-0.69

 irmãos

-0.62

Parfait

-0.60

 estrella

-0.56

 höchst

-0.56

ásban

-0.55

例文帳に追加

-0.54

QMetaType

-0.53

"])){

-0.53

 estrela

-0.53

POSITIVE LOGITS

fifty

0.85

Fifty

0.84

 fifty

0.81

 Fifty

0.78

 FetchType

0.76

AndEndTag

0.73

NOPQRST

0.71

 GenerationType

0.70

bootstrapcdn

0.70

chenta

0.69

Activations Density 0.248%

numerical values and measurements within the document

No Comments

No Known Activations