INDEX

Explanations

terms and phrases related to identification documents and their verification process

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

!*\

-0.92

 myſelf

-0.86

 uſed

-0.84

 Jefus

-0.83

 itſelf

-0.83

 ་་

-0.81

 betweenstory

-0.81

parsedMessage

-0.81

^(@)

-0.80

 saites

-0.79

POSITIVE LOGITS

 pass

0.59

 Pass

0.57

 card

0.50

pass

0.50

 Show

0.50

ID

0.50

Pass

0.49

 peme

0.48

ob

0.45

 cards

0.45

Activations Density 0.175%

terms and phrases related to identification documents and their verification process

No Comments

No Known Activations