INDEX

Explanations

patterns in structured programming syntax, specifically related to C or similar languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 nakalista

-0.83

StructEnd

-0.71

 resourceCulture

-0.70

ViewFeatures

-0.63

 estimés

-0.57

 ostavi

-0.56

IsContent

-0.54

Pey

-0.53

✭✭

-0.52

HasAnnotation

-0.51

POSITIVE LOGITS

tableFuture

0.73

GEBURTS

0.70

BASEPATH

0.69

Bissau

0.66

 StatefulWidget

0.66

 StatelessWidget

0.65

#+#

0.63

 Weeknd

0.62

GOTREF

0.62

*>(

0.60

Activations Density 0.058%

patterns in structured programming syntax, specifically related to C or similar languages

No Comments

No Known Activations