INDEX

Explanations

symbols related to brand logos or trademarks

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

-0.73

tum

-0.60

Nils

-0.60

dej

-0.59

ल

-0.59

-0.58

jil

-0.55

cri

-0.54

POSITIVE LOGITS

aarrggbb

1.15

 NSCoder

1.13

ьаж

0.94

 engraçadas

0.94

djangoproject

0.93

XmlEnum

0.92

Diweddarwch

0.91

 Sequo

0.91

 Roskov

0.91

antMatchers

0.90

Activations Density 0.000%

No Known Activations