INDEX

Explanations

annotations indicating the nullability and non-nullability of variables or parameters in programming code

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

MessageTagHelper

-0.80

mapStateToProps

-0.76

 كومونز

-0.72

ⓧ

-0.68

 RoutedEventArgs

-0.68

 GenerationType

-0.66

 AppModule

-0.64

 JAXBElement

-0.62

StoryboardSegue

-0.61

findpost

-0.60

POSITIVE LOGITS

NonNull

2.93

Nonnull

1.82

NotNull

1.45

Nullable

1.29

requireNonNull

0.70

Демографія

0.64

Nek

0.64

 migrator

0.63

 Réponses

0.62

(!__

0.61

Activations Density 0.019%

annotations indicating the nullability and non-nullability of variables or parameters in programming code

No Comments

No Known Activations