INDEX

Explanations

legal and regulatory terminology related to guilt and penalties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ValueStyle

-0.79

 esternos

-0.76

mybatisplus

-0.73

 StatefulWidget

-0.70



-0.65

发表于

-0.63

SOUNDBITE

-0.61

 RoutedEventArgs

-0.60

 autorytatywna

-0.60

 LoggerFactory

-0.60

POSITIVE LOGITS

 punishment

1.83

 penalty

1.61

 penalties

1.56

 punished

1.56

 punishments

1.52

 disciplinary

1.47

 Punishment

1.47

 punish

1.40

 penal

1.39

 fines

1.34

Activations Density 1.184%

legal and regulatory terminology related to guilt and penalties

No Comments

No Known Activations