INDEX

Explanations

references to specific individuals and their roles or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

وفاته

-0.75

 męski

-0.75

 himself

-0.69

 męskie

-0.65

 móg

-0.65

himself

-0.64

 zijne

-0.64

 sám

-0.63

 boyhood

-0.61

‍♂️

-0.61

POSITIVE LOGITS

 herself

0.97

 businesswoman

0.68

 lesbian

0.65

 feminist

0.63

herself

0.63

 woman

0.61

 motherhood

0.60

 womanhood

0.58

 girl

0.57

 goddess

0.57

Activations Density 2.304%

references to specific individuals and their roles or actions

No Comments

No Known Activations