INDEX

Explanations

phrases indicating absoluteness or extremity in statements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Serikat

-0.47

both

-0.46

벗

-0.43

 Klicken

-0.42

ortal

-0.42

visualization

-0.42

 ascorbic

-0.42

 trì

-0.42

 cutaneous

-0.42

 visualization

-0.42

POSITIVE LOGITS

 Мексичка

0.97

 تضيفلها

0.73

 محفوظة

0.70

+#+

0.70

########.

0.69

leece

0.67

 okuyayım

0.67

Obrázky

0.67

 виправивши

0.65

+#+#

0.65

Activations Density 0.421%

phrases indicating absoluteness or extremity in statements

No Comments

No Known Activations