INDEX

Explanations

code snippets that denote initialization or clearing of variables

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76

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

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

adaptiveStyles

-0.70

 continuant

-0.60

Collegamenti

-0.59

imageshack

-0.56

حوالہ

-0.52

 ListTile

-0.52

 anstatt

-0.50

IndentedString

-0.50

idados

-0.48

Дереккөздер

-0.48

POSITIVE LOGITS

endphp

0.80

mapStateToProps

0.65

bootstrapcdn

0.62

apimachinery

0.58

%");

0.57

GOTREF

0.56

 whiteColor

0.56

 мәкал

0.56

ณ์

0.55

:"-"`

0.55

Activations Density 0.026%

code snippets that denote initialization or clearing of variables

No Comments

No Known Activations