INDEX

Explanations

content related to phishing and online scams

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

VersionUID

-0.86

tvguidetime

-0.85

GIVEREF

-0.72

ArgsConstructor

-0.72

 ProtoMessage

-0.72

GOTREF

-0.71

Personensuche

-0.71

IContainer

-0.69

 CreateTagHelper

-0.68

 &___

-0.66

POSITIVE LOGITS

 tale

0.49

Scam

0.48

 scam

0.48

 scams

0.46

vic

0.43

 Scam

0.43

 scammed

0.41

ഭ

0.41

 scammer

0.40

 starred

0.40

Activations Density 0.043%

content related to phishing and online scams

No Comments

No Known Activations