INDEX

Explanations

phrases and expressions that indicate a positive sentiment or description

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

 disponibilités

-0.84

 wikipagina

-0.82

GEBURTSDATUM

-0.82

mybatisplus

-0.79

DropTable

-0.76

 चीज़ों

-0.75

enterOuterAlt

-0.73

таратура

-0.72

 متعلقه

-0.70

LookAnd

-0.70

POSITIVE LOGITS

 also

0.57

It

0.56

 mobili

0.56

It

0.56

 certainly

0.55

folge

0.53

 همچنین

0.52

ش

0.52

 ayrıca

0.51

However

0.51

Activations Density 0.378%

phrases and expressions that indicate a positive sentiment or description

No Comments

No Known Activations