INDEX

Explanations

references to artificial entities or substances in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Préférences

-0.80

তথ্যসূত্র

-0.79

grà

-0.79

 familiale

-0.78

 Portail

-0.78

 primaire

-0.78

amaño

-0.77

 المعيارى

-0.77

DrawerLayout

-0.77

ükü

-0.77

POSITIVE LOGITS

 fake

1.63

 Fake

1.45

 artificial

1.43

fake

1.42

 Artificial

1.39

Fake

1.38

artificial

1.32

Artificial

1.28

 faux

1.21

 fakes

1.12

Activations Density 0.246%

references to artificial entities or substances in various contexts

No Comments

No Known Activations