INDEX

Explanations

numerical data and statistical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 <<<<<<<<<<<<<<

-0.86

 HttpNotFound

-0.83

RTLD

-0.80

AsUp

-0.78

 GreatSchools

-0.73

 AssemblyTitle

-0.71

 defaultstate

-0.70

 AssemblyCulture

-0.70

featureID

-0.69

 nahilalakip

-0.69

POSITIVE LOGITS

::_('

0.58

Portail

0.57

glTranslatef

0.54

Ear

0.53

ίδι

0.50

wpi

0.49

UnifiedTopology

0.49

州市

0.49

lod

0.48

Tazama

0.48

Activations Density 1.458%

numerical data and statistical terms

No Comments

No Known Activations