INDEX

Explanations

indications of government-related qualities or qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

entially

-0.57

pportun

-0.56

OMEN

-0.55

IFORNIA

-0.54

ſhip

-0.54

TryParse

-0.54

ICING

-0.53

aka

-0.52

unately

-0.52

textnormal

-0.52

POSITIVE LOGITS

 kaarangay

0.70

GEBURTSDATUM

0.67

AndEndTag

0.66

فایل‌لار

0.64

 naturali

0.63

uxxxx

0.62

 المعيارى

0.62

 Krakowie

0.61

 malattie

0.61

 pensioners

0.61

Activations Density 0.302%

indications of government-related qualities or qualifications

No Comments

No Known Activations