INDEX

Explanations

references to universities and geographical locations

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

uolo

-0.79

 Itália

-0.75

 Italy

-0.72

 Italian

-0.71

 Italia

-0.65

Italy

-0.64

stery

-0.64

DataAnnotations

-0.63

 italianos

-0.63

 Italijani

-0.63

POSITIVE LOGITS

 يتيمه

0.88

 tfsi

0.75

 sandero

0.74

NamedQueries

0.72

basicConfig

0.71

LookAnd

0.69

 vantaggio

0.69

 Monfieur

0.69

 himſelf

0.67

 Bolsa

0.65

Activations Density 1.509%

references to universities and geographical locations

No Comments

No Known Activations