INDEX

Explanations

terms and phrases related to database management and permissions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ardige

-0.83

 nahilalakip

-0.79

 bezeichneter

-0.78

 &___

-0.70

niająca

-0.69

+#+

-0.68

 Exacts

-0.65

AutoScale

-0.65

balleur

-0.63

 correctes

-0.62

POSITIVE LOGITS

的

0.44

tabel

0.44

گون

0.42

isset

0.42

 Intern

0.41

的多

0.40

 Deja

0.39

がち

0.39

 userManager

0.39

sslich

0.39

Activations Density 0.026%

terms and phrases related to database management and permissions

No Comments

No Known Activations