INDEX

Explanations

words associated with criticism, mockery, and satire of societal behaviors and political actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 EconPapers

-0.90

 Signalez

-0.73

 Exacts

-0.67

 VIAF

-0.64

WriteAttribute

-0.60

unsplash

-0.56

KommentareTeilen

-0.56

 "..\..\

-0.55

XMLSchema

-0.54

 SEDS

-0.53

POSITIVE LOGITS

 stupidity

1.29

 shame

1.27

 hypocrisy

1.25

 foolishness

1.21

 mockery

1.20

 fools

1.18

 foolish

1.18

 mocking

1.18

 ridicule

1.17

 ignorance

1.15

Activations Density 2.216%

words associated with criticism, mockery, and satire of societal behaviors and political actions

No Comments

No Known Activations