INDEX

Explanations

statements or phrases indicating a sequence or summary of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 well

-1.01

 soon

-0.79

well

-0.67

 hyvin

-0.60

soon

-0.60

 dobrze

-0.59

Well

-0.56

 Well

-0.54

 хорошо

-0.53

 WELL

-0.52

POSITIVE LOGITS

<bos>

0.76

WebElementEntity

0.49

 مشين

0.49

 betweenstory

0.49

elemField

0.49

 فريبيس

0.46

 հղումներ

0.46

UnitTesting

0.44

قایناقلار

0.44

BeginContext

0.42

Activations Density 0.247%

statements or phrases indicating a sequence or summary of information

No Comments

No Known Activations