INDEX

Explanations

occurrences of user interface (UI) elements and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 للمعارف

-1.12

脚注の使い方

-0.94

ImageContext

-0.84

NameInMap

-0.84

 tartalomajánló

-0.83

 HasFactory

-0.81

 AssemblyCulture

-0.79

Tikang

-0.79

出版年

-0.78

帖最后由

-0.78

POSITIVE LOGITS

UI

0.69

UI

0.69

0.57

Ui

0.55

 tender

0.53

Ui

0.52

 asegur

0.49

0.48

ui

0.47

ui

0.46

Activations Density 0.192%

occurrences of user interface (UI) elements and their attributes

No Comments

No Known Activations