INDEX

Explanations

instances where uncertainty or questions about knowledge are expressed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 propOrder

-0.67

Xna

-0.62

endregion

-0.60

bsen

-0.57

asable

-0.56

isand

-0.55

indler

-0.54

 betweenstory

-0.54

IsContent

-0.54

reactivex

-0.54

POSITIVE LOGITS

 يتيمه

0.73

 disambiguazione

0.70

 unknow

0.69

GEBURTSDATUM

0.68

 wierd

0.65

Dunno

0.65

 vetorial

0.61

UrlResolution

0.60

 preliminar

0.60

 dunno

0.60

Activations Density 0.125%

instances where uncertainty or questions about knowledge are expressed

No Comments

No Known Activations