INDEX

Explanations

structure and organization in written documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

sizeCache

-0.83

 autorytatywna

-0.70

Personensuche

-0.68

 Мексичка

-0.68

ContentAsync

-0.66

Filmografie

-0.62

Vanjske

-0.62

Externé

-0.62

FieldBuilder

-0.61

 ویکی‌پدیا

-0.61

POSITIVE LOGITS

 Herod

0.47

ẵng

0.43

yeur

0.43

endpush

0.43

 đừng

0.43

었습니다

0.42

drawSprites

0.42

 autocorrelation

0.42

livan

0.40

 difp

0.40

Activations Density 0.320%

structure and organization in written documents

No Comments

No Known Activations