INDEX

Explanations

mentions of the word "series."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

cshtml

-0.68

 notizia

-0.66

脚注の使い方

-0.63

addWidget

-0.63

ysacchar

-0.61

heast

-0.61

lihood

-0.60

 toothpick

-0.56

dshaw

-0.54

mapStateToProps

-0.54

POSITIVE LOGITS

 series

4.21

 Series

3.75

series

3.71

Series

3.69

 SERIES

3.62

SERIES

3.11

 serie

2.77

 série

2.64

 séries

2.48

serie

2.35

Activations Density 0.038%

mentions of the word "series."

No Comments

No Known Activations