INDEX

Explanations

phrases related to the likelihood or possibility of events happening

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

存于互联网档案馆

-0.71

BeginContext

-0.66

WEBPACK

-0.65

TagHelpers

-0.63

jago

-0.62

__(/*!

-0.57

enumi

-0.56

 Wellen

-0.55

 Erwachsene

-0.55

cznych

-0.54

POSITIVE LOGITS

 chances

1.82

 chance

1.77

chance

1.57

 Chances

1.56

 CHANCE

1.50

Chances

1.49

 Chance

1.40

Chance

1.36

 шан

1.31

 likelihood

1.18

Activations Density 0.279%

phrases related to the likelihood or possibility of events happening

No Comments

No Known Activations