INDEX

Explanations

geographic locations and addresses

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Autoritní

-0.81

kháu

-0.81

 itſelf

-0.80

 дописавши

-0.79

تقاوى

-0.78

parsedMessage

-0.78

 незавершена

-0.77

isContained

-0.74

Personendaten

-0.73

 Moslem

-0.71

POSITIVE LOGITS

 North

0.54

Al

0.51

De

0.51

 South

0.50

 Avenue

0.50

0.48

шай

0.48

0.45

Mat

0.45

 East

0.45

Activations Density 0.206%

geographic locations and addresses

No Comments

No Known Activations