INDEX

Explanations

terms and elements related to tabbed interfaces and layouts in user interface design

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

 Kongo

-0.73

 Vinci

-0.72

Aiheesta

-0.70

 ?>">

-0.68

?>

-0.68

끗

-0.66

Vinci

-0.66

']}

-0.65

"</

-0.65

ésia

-0.65

POSITIVE LOGITS

tab

2.31

Tab

2.15

Tab

2.10

 tabs

2.07

tab

2.00

 Tabs

1.96

TAB

1.80

tabs

1.76

TAB

1.71

Tabs

1.59

Activations Density 0.054%

terms and elements related to tabbed interfaces and layouts in user interface design

No Comments

No Known Activations