INDEX

Explanations

markup indicating the start of sections or categories in a document

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

NewLabel

-0.60

withstanding

-0.59

первых

-0.58

<()>

-0.56

hala

-0.55

 RoutedEventArgs

-0.54

 characteristic

-0.53

 onAnimation

-0.52

PhysRev

-0.52

 parallel

-0.52

POSITIVE LOGITS

CWE

0.74

AxisAlignment

0.73

HostException

0.72

harusnya

0.71

 morire

0.70

 endregion

0.68

ногие

0.68

LayoutConstraint

0.66

Numerology

0.64

TagMode

0.63

Activations Density 0.298%

markup indicating the start of sections or categories in a document

No Comments

No Known Activations