INDEX

Explanations

references to gender diversity and representation in media

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

representation or demographics

np_acts-logits-general · gemini-2.0-flash

demographic representation of groups

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

SuspendLayout

-0.40

 zwey

-0.38

 schönen

-0.38

 Umbau

-0.37

 Grüsse

-0.37

เพิ่มเติม

-0.36

 igång

-0.36

誰でも

-0.35

 سرو

-0.35

 actionMode

-0.35

POSITIVE LOGITS

 representation

0.63

 pinulongan

0.54

 للمعارف

0.52

WriteBarrier

0.51

 participation

0.50

representation

0.49

 Representation

0.49

 оригіналу

0.48

Representation

0.47

 representations

0.46

Activations Density 0.536%

references to gender diversity and representation in media

representation or demographics

demographic representation of groups

No Comments

No Known Activations