INDEX

Explanations

terms related to discrimination and stigma, particularly in the context of marginalized groups

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

 viewDidLoad

-0.82

findpost

-0.76

Initializable

-0.70

alamus

-0.67

idopsis

-0.67

GEBURTSDATUM

-0.64

nteral

-0.63

/***/

-0.62

ertos

-0.62

 EconPapers

-0.61

POSITIVE LOGITS

 discrimination

1.36

 Discrimination

1.08

 prejudice

1.07

 discriminated

1.04

discrimination

1.03

crimination

1.02

 discriminate

1.00

 discriminatory

0.99

judice

0.95

 racism

0.95

Activations Density 0.285%

terms related to discrimination and stigma, particularly in the context of marginalized groups

No Comments

No Known Activations