INDEX

Explanations

terms associated with illegal activities or law violations

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

Preceding words of actions or behaviors, often unlawful

np_acts-logits-general · gemini-2.0-flash

illegal activity or behavior

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

adaptiveStyles

-0.92

 تضيفلها

-0.78

 <>",

-0.77

IVEREF

-0.74

 AssemblyCulture

-0.74

 مرئيه

-0.73

ConstraintMaker

-0.71

 Administrativna

-0.70

 INTERESAR

-0.70

 NSCoder

-0.69

POSITIVE LOGITS

 activity

0.78

 activities

0.72

 behavior

0.61

 actions

0.60

 behaviour

0.56

activity

0.56

 actividad

0.55

activities

0.55

 practices

0.54

 Activities

0.53

Activations Density 0.431%

terms associated with illegal activities or law violations

Preceding words of actions or behaviors, often unlawful

illegal activity or behavior

No Comments

No Known Activations