INDEX

Explanations

terms associated with scientific evaluation and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

leby

-0.75

/\.

-0.69

 MonoBehaviour

-0.68

Formazione

-0.67

 AssemblyCompany

-0.66

UserScript

-0.62

듭

-0.61

 calendriers

-0.60

PickerController

-0.60

enumi

-0.60

POSITIVE LOGITS

by

0.81

 الفلك

0.61

to

0.59

 into

0.59

as

0.58

 Wikimedijinoj

0.57

 isInitialized

0.57

 again

0.56

 ahead

0.56

Jeografia

0.54

Activations Density 1.222%

terms associated with scientific evaluation and analysis

No Comments

No Known Activations