INDEX

Explanations

numbers and technical specifications related to products or standards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تضيفلها

-0.74

 дописавши

-0.72

 Paglinawan

-0.67

 ISNI

-0.66

isome

-0.65

دانشنامهٔ

-0.64

tagext

-0.64

 AssemblyCulture

-0.62

WebElementEntity

-0.62

addContainerGap

-0.61

POSITIVE LOGITS

tvguidetime

0.64

פיה

0.49

 would

0.48

 looking

0.46

 Moments

0.46

nuo

0.45

 AppComponent

0.45

}{|

0.44

AppComponent

0.44

lní

0.43

Activations Density 0.945%

numbers and technical specifications related to products or standards

No Comments

No Known Activations