INDEX

Explanations

references to size and fitting specifications

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

VYMaps

-0.44

-------

-0.39

tagHelperRunner

-0.38

BeginInit

-0.32

 lembran

-0.31

 genieten

-0.31

 okuyayım

-0.30

*>(

-0.30

[]>(

-0.30

 gewiß

-0.29

POSITIVE LOGITS

 grade

0.74

XmlAccessorType

0.73

+#+

0.70

 GRADE

0.69

:✨

0.69

Personendaten

0.69

 Grade

0.69

 juſ

0.68

 Sizing

0.67

 SIZES

0.67

Activations Density 0.591%

references to size and fitting specifications

No Comments

No Known Activations