INDEX

Explanations

concepts related to protection and privacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

yonel

-0.58

CascadeType

-0.57

hoga

-0.56

外部リンク

-0.56

انيف

-0.55

مصادر

-0.53

ък

-0.51

 CascadeType

-0.51

Pov

-0.48

 Roskov

-0.48

POSITIVE LOGITS

 protect

1.40

 protects

1.38

 Protects

1.37

 protecting

1.37

 Protect

1.33

protect

1.30

Protect

1.27

 Protecting

1.22

Protecting

1.21

 PROTECT

1.20

Activations Density 0.123%

concepts related to protection and privacy

No Comments

No Known Activations