INDEX

Explanations

phrases related to questions and responses about identity and personal experiences

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

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

TagHelper

-0.66

AnchorStyles

-0.63

 <=",

-0.63

Diweddarwch

-0.56

 mahdol

-0.56

 Meksiku

-0.53

 Infórmanos

-0.53

ArrowToggle

-0.52

 mulig

-0.50

Tembelea

-0.49

POSITIVE LOGITS

everywhere

0.64

↩

0.63

 Everywhere

0.63

 CreateTagHelper

0.61

httphttps

0.61

 anywhere

0.59

 nowadays

0.59

anywhere

0.59

SetItem

0.58

writeFieldEnd

0.57

Activations Density 0.112%

phrases related to questions and responses about identity and personal experiences

No Known Activations