INDEX

Explanations

references to user interface elements and widgets in coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

={\

-0.59

WithFormat

-0.57

Aiheesta

-0.56

>*/

-0.52

obr

-0.51

 كومونز

-0.50

)|(

-0.50

Hochspringen

-0.49

protoimpl

-0.49

putation

-0.49

POSITIVE LOGITS

 widgets

0.90

setupUi

0.83

 Widget

0.83

 widget

0.82

 Widgets

0.81

 createState

0.78

Widget

0.75

widget

0.74

 يتيمه

0.70

widgets

0.70

Activations Density 0.018%

references to user interface elements and widgets in coding contexts

No Comments

No Known Activations