INDEX

Explanations

terms related to legal justifications and misconduct in detention facilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

RefNanny

-0.57

Референце

-0.56

folger

-0.52

 StatelessWidget

-0.51

 Privacidade

-0.51

czegó

-0.50

 pointer

-0.49

 hagy

-0.49

χαν

-0.48

 mirror

-0.48

POSITIVE LOGITS

 thereafter

1.07

 subsequent

1.04

 Thereafter

1.04

 afterwards

0.95

 Subsequent

0.90

 afterward

0.90

 subsequently

0.87

 Subsequently

0.84

 Afterwards

0.84

Afterwards

0.81

Activations Density 0.887%

terms related to legal justifications and misconduct in detention facilities

No Comments

No Known Activations