INDEX

Explanations

terms related to fraudulent activities and scams

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 force

-0.36

 poll

-0.28

 table

-0.28

 soft

-0.24

 bright

-0.24

dai

-0.24

pe

-0.24

key

-0.23

da

-0.23

ั่ง

-0.23

POSITIVE LOGITS

 scams

0.91

 Италијани

0.91

 للمعارف

0.88

 للاسماء

0.87

 Scam

0.86

Scam

0.85

詐欺

0.85

Fraud

0.84

 scammers

0.84

 scam

0.84

Activations Density 0.391%

terms related to fraudulent activities and scams

No Comments

No Known Activations