INDEX

Explanations

mentions of financial transactions or payments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

\{\\

-1.06

 Glou

-0.90

avax

-0.81

 Holtz

-0.74

LookAnd

-0.71

 חיצוניים

-0.70

olja

-0.70

 Hess

-0.70

/>\

-0.69

 Hesse

-0.69

POSITIVE LOGITS

 Paid

1.93

 paid

1.89

Paid

1.84

paid

1.76

 PAID

1.76

PAID

1.45

 pagado

0.95

 payed

0.91

 unpaid

0.88

 bezahlt

0.79

Activations Density 0.117%

mentions of financial transactions or payments

No Comments

No Known Activations