INDEX

Explanations

mentions of specific organizations or brands associated with charitable work

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

that often precede adjectives

np_acts-logits-general · gemini-2.0-flash

iconic individuals and superstars

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

PRWEB

-0.63

 lokal

-0.61

 lokale

-0.61

SourceChecksum

-0.61

市镇

-0.60

StoryboardSegue

-0.59

Життєпис

-0.57

XmlAccessType

-0.56

 pleasantly

-0.56

Lokal

-0.56

POSITIVE LOGITS

 world

0.74

 billions

0.71

 Nobel

0.70

 iconic

0.68

 mega

0.64

Nobel

0.63

 World

0.62

 superstar

0.60

 दुनिया

0.59

 famous

0.59

Activations Density 0.502%

mentions of specific organizations or brands associated with charitable work

that often precede adjectives

iconic individuals and superstars

No Comments

No Known Activations