INDEX

Explanations

phrases related to data security and privacy practices

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

"security"

np_acts-logits-general · gemini-2.0-flash

security

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

ⓧ

-0.72

EDEFAULT

-0.64

存于互联网档案馆

-0.51

 ModelExpression

-0.51

出版年

-0.51

 CreateTagHelper

-0.51

السكان

-0.49

 nakalista

-0.49

stellungs

-0.48

Gön

-0.47

POSITIVE LOGITS

 security

2.30

security

1.94

 Security

1.93

Security

1.88

 SECURITY

1.76

 secure

1.71

SECURITY

1.70

 Secure

1.63

Secure

1.53

secure

1.50

Activations Density 0.512%

phrases related to data security and privacy practices

"security"

security

No Comments

No Known Activations