INDEX

Explanations

intensifiers and modifiers that emphasize or diminish the magnitude of qualities or situations

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

-0.48

gameserver

-0.47

ReusableCell

-0.45

“

-0.41

 sendiri

-0.41

na

-0.39

 roving

-0.38

Tra

-0.38

gel

-0.38

POSITIVE LOGITS

tagHelperRunner

1.20

Personensuche

0.95

AccessorTable

0.93

fjspx

0.87

WebElementEntity

0.83

ftagPool

0.83

انيف

0.81

RegistryLite

0.81

GEBURTSDATUM

0.79

protoimpl

0.78

Activations Density 0.276%

intensifiers and modifiers that emphasize or diminish the magnitude of qualities or situations

No Comments

No Known Activations