INDEX

Explanations

categories and classifications related to geographical locations and demographics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

UnusedPrivate

-0.61

WebElementEntity

-0.59

 Meksiku

-0.56

awtextra

-0.56

tanleria

-0.55

oa̍t

-0.52

Derbyniad

-0.52

 pinulongan

-0.52

IUrlHelper

-0.50

EndInit

-0.49

POSITIVE LOGITS

Template

0.55

 Template

0.54

–

0.51

ุก

0.46

ⓦ

0.46

 shit

0.42

 invited

0.42

 List

0.40

chy

0.39

SFER

0.39

Activations Density 1.487%

categories and classifications related to geographical locations and demographics

No Comments

No Known Activations