INDEX

Explanations

references to race, ethnicity, and power structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

MigrationBuilder

-0.65

الحياه

-0.61

URLException

-0.57

 članak

-0.57

 bacio

-0.56

 bazen

-0.54

 manchmal

-0.54

 appréci

-0.53

 cappello

-0.53

TagMode

-0.53

POSITIVE LOGITS

 propaganda

0.87

 propagan

0.77

 Soros

0.76

 Rothschild

0.73

 indoctr

0.71

 cabal

0.69

 corrupt

0.69

 Fauci

0.68

 Biden

0.67

(((

0.66

Activations Density 0.867%

references to race, ethnicity, and power structures

No Comments

No Known Activations