INDEX

Explanations

terms associated with scams and fraudulent practices

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

scams or fraudulent activities

np_acts-logits-general · gemini-2.0-flash

scam and fraud

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 surla

-0.91

 AssemblyTitle

-0.74

 ExecuteAsync

-0.69

 ivelany

-0.65

 Réponses

-0.64

 AssemblyProduct

-0.60

期刊论文

-0.60

 مرئيه

-0.59

OGND

-0.58

Datuak

-0.58

POSITIVE LOGITS

 scam

1.64

 scams

1.59

 scammers

1.39

 fraud

1.38

Scam

1.38

 fraudulent

1.38

 Scam

1.31

 scammer

1.29

 frauds

1.28

 scammed

1.28

Activations Density 0.245%

terms associated with scams and fraudulent practices

scams or fraudulent activities

scam and fraud

No Comments

No Known Activations