INDEX

Explanations

words associated with societal issues and controversies surrounding LGBTQ+ topics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.56

-0.53

↵↵

-0.51

↵

-0.44

Джерела

-0.42

 nueces

-0.41

Välislingid

-0.41

-0.39

<sup>

-0.38

//

-0.38

POSITIVE LOGITS

 kasarigan

1.28

 متعلقه

1.28

DebuggerNonUser

1.27

IsContent

1.24

 myſelf

1.11

Билгалдахарш

1.05

 itſelf

1.03

 himſelf

0.98

 فريبيس

0.97

 betweenstory

0.95

Activations Density 2.976%

words associated with societal issues and controversies surrounding LGBTQ+ topics

No Comments

No Known Activations