INDEX

Explanations

specific contact information and details related to communication channels or notifications

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

Contact information

np_acts-logits-general · gemini-2.0-flash

addresses, names, URLs

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

OGND

-0.63

 nahilalakip

-0.58

 ProtoMessage

-0.53

BooleanField

-0.50

igneurs

-0.49

 Tại

-0.49

saraba

-0.49

endgroup

-0.49

 चीज़ों

-0.48

omethane

-0.48

POSITIVE LOGITS

 addresses

0.89

 names

0.85

 URLs

0.83

 address

0.83

URL

0.74

 adresses

0.73

 Addresses

0.72

 coordinates

0.69

地址

0.68

 whereabouts

0.65

Activations Density 0.425%

specific contact information and details related to communication channels or notifications

Contact information

addresses, names, URLs

No Comments

No Known Activations