INDEX

Explanations

derogatory terms and negative descriptions related to individuals or groups

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

BeginInit

-0.73

ConstraintMaker

-0.71

StoreMessageInfo

-0.69

GraphicsUnit

-0.68

tanleria

-0.65

 againſt

-0.64

 utafitiHapana

-0.63

 AppCompatTheme

-0.63

contentLoaded

-0.63

 händ

-0.63

POSITIVE LOGITS

 scum

0.70

 unfit

0.60

 shameless

0.60

 incompetent

0.59

 lazy

0.59

 worthless

0.59

 greedy

0.58

ped

0.58

sc

0.57

 immoral

0.57

Activations Density 0.413%

derogatory terms and negative descriptions related to individuals or groups

No Comments

No Known Activations