INDEX

Explanations

references to age or years

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

Age in years/months followed by "old"

np_acts-logits-general · gemini-2.0-flash

years old or months old

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Datuak

-0.90

verifyException

-0.69

NameInMap

-0.68

TintMode

-0.65

intios

-0.62

 Réponses

-0.62

AccessorTable

-0.60

saraba

-0.58

клопе

-0.56

XmlRootElement

-0.56

POSITIVE LOGITS

old

2.59

old

2.01

Old

1.56

Old

1.53

OLD

1.53

OLD

1.45

 olds

1.45

 oude

1.39

 vieux

1.39

 vecchio

1.38

Activations Density 0.112%

references to age or years

Age in years/months followed by "old"

years old or months old

No Comments

No Known Activations