INDEX

Explanations

numerical values associated with data measures or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Zeneca

-0.69

skechers

-0.67

}],

-0.65

født

-0.61

 AssemblyVersion

-0.60

ViewFeatures

-0.59

 createState

-0.58

 побу

-0.57

MessageOf

-0.57

__':

-0.57

POSITIVE LOGITS

IndentedString

0.65

AttributeSet

0.56

 متعلقه

0.56

Clik

0.55

 Besten

0.52

 resourceCulture

0.51

 autorytatywna

0.50

 Erfol

0.50

 Stücke

0.49

nativeElement

0.48

Activations Density 0.137%

numerical values associated with data measures or results

No Comments

No Known Activations