INDEX

Explanations

references to individuals, regions, and organizations related to law, criticism, and social responsibility

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

 Bunt

-0.77

 Cyclops

-0.76

 Shogun

-0.73

 Buka

-0.70

 tvar

-0.69

almaz

-0.69

 Deviant

-0.68

Fag

-0.68

 Bruxelles

-0.66

 Mauri

-0.66

POSITIVE LOGITS

 referenties

0.90

 surla

0.84

 дописавши

0.77

 autorytatywna

0.76

 Winaray

0.75

GEBURTSDATUM

0.72

abestanden

0.71

بوابة

0.71

vière

0.71

ыгана

0.70

Activations Density 2.025%

references to individuals, regions, and organizations related to law, criticism, and social responsibility

No Comments

No Known Activations