INDEX

Explanations

questions and queries about important information or topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Aze

-0.78

 brook

-0.71

OfYear

-0.71

 hoffe

-0.70

lindung

-0.69

LINE

-0.68

 Verge

-0.68

 Pollack

-0.67

ze

-0.66

timbangkan

-0.66

POSITIVE LOGITS

 what

1.99

 WHAT

1.89

what

1.89

What

1.85

WHAT

1.84

 What

1.80

whats

1.13

Whats

1.03

 quelles

1.02

Τι

1.01

Activations Density 0.115%

questions and queries about important information or topics

No Comments

No Known Activations