INDEX

Explanations

references to popular culture and celebrity involvement in media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 propOrder

-0.66

مقاله

-0.65

 opium

-0.64

SOUNDBITE

-0.62

 Réponses

-0.60

 assolu

-0.60

KURZBESCHREIBUNG

-0.59

ंदीखरीदारी

-0.58

 Opium

-0.58

 Gallimard

-0.56

POSITIVE LOGITS

 comedies

0.60

 laugh

0.60

 hilarious

0.59

 funnier

0.55

 laughs

0.55

 humor

0.54

 коме

0.54

 laughter

0.54

 funniest

0.53

ตล

0.53

Activations Density 0.131%

references to popular culture and celebrity involvement in media

No Comments

No Known Activations