INDEX

Explanations

words and syntax related to programming and graphical layout structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Upper

-0.90

 Upper

-0.89

 upper

-0.86

 للمعارف

-0.78

upper

-0.77

HasAnnotation

-0.76

 upwards

-0.72

 getHeight

-0.71

 UPPER

-0.70

 upstairs

-0.69

POSITIVE LOGITS

 erkek

0.78

 male

0.77

 boyfriend

0.77

 männ

0.76

 masculina

0.76

 husbands

0.76

 mężczy

0.76

 husband

0.72

 męskie

0.72

 males

0.72

Activations Density 0.143%

words and syntax related to programming and graphical layout structure

No Comments

No Known Activations