INDEX

Explanations

references to geographical locations and political entities, particularly the United States and related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 allAfrica

-0.78

 مواليد

-0.69

DoubleQuotes

-0.69

 myſelf

-0.68

 disponibilités

-0.67

verwijspagina

-0.66

ViewImports

-0.65

 Lightboxes

-0.64

 countryside

-0.62

 Performer

-0.60

POSITIVE LOGITS

dojo

0.47

 presenti

0.44

Xna

0.44

ždý

0.44

 statunitense

0.43

esez

0.43

setContentView

0.42

जू

0.41

Or

0.41

AndEndTag

0.41

Activations Density 0.542%

references to geographical locations and political entities, particularly the United States and related contexts

No Comments

No Known Activations