INDEX

Explanations

numerical data and statistical elements in text

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

 مشين

-0.75

 kasarigan

-0.74

GEBURTSDATUM

-0.71

CloseOperation

-0.68

ⓧ

-0.68

 وتسجيلات

-0.67

 المعيارى

-0.66



-0.66

سطس

-0.66

 ivelany

-0.64

POSITIVE LOGITS

 Fourteen

0.51

 fourteen

0.48

ieszka

0.48

十九

0.48

 nineteen

0.45

Thirteen

0.45

 fourteenth

0.45

Fifteen

0.44

ıyors

0.44

urman

0.44

Activations Density 0.391%

numerical data and statistical elements in text

No Comments

No Known Activations