INDEX

Explanations

references to educational activities and student engagement

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

хьтан

-0.85

 Whilst

-0.84

Whilst

-0.82

 avoient

-0.82

 صوتيه

-0.81

 poichè

-0.80

 négociations

-0.79

 daß

-0.77

AndEndTag

-0.75

 skall

-0.74

POSITIVE LOGITS

“

0.69

pan

0.57

0.54

—

0.54

scu

0.50

 temp

0.50

три

0.49

end

0.49

Activations Density 0.280%

No Known Activations