INDEX

Explanations

email addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

AndEndTag

-1.12

setVerticalGroup

-1.08

$_['

-0.82

RegistryLite

-0.81

хьтан

-0.78

 kasarigan

-0.77

TagMode

-0.77

NameInMap

-0.75

 ModelRenderer

-0.75

RenderAtEndOf

-0.75

POSITIVE LOGITS

gmail

1.03

blogspot

0.85

 gmail

0.74

hotmail

0.65

yahoo

0.63

appspot

0.58

 Gmail

0.55

weebly

0.51

aol

0.47

google

0.47

Activations Density 0.055%

email addresses

No Comments

No Known Activations