INDEX

Explanations

instances of the word "In" and variations of citations in academic writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

tvguidetime

-0.86

 juſ

-0.73

 fubject

-0.71

 betweenstory

-0.71

 passés

-0.71

 Biôgrafia

-0.69

 Wicidata

-0.67

 ſeveral

-0.67

 joaat

-0.66

 diſt

-0.66

POSITIVE LOGITS

 kasarigan

0.64

in

0.51

 Serikat

0.51

NCR

0.47

 الاطلاع

0.47

ölkerung

0.46

Czytaj

0.46

 dalam

0.46

 AttributeSet

0.45

pered

0.45

Activations Density 0.524%

instances of the word "In" and variations of citations in academic writing

No Comments

No Known Activations