INDEX

Explanations

references to inventions or presentations of new concepts and findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 estekak

-0.73

Autoritní

-0.56

Rujuakan

-0.55

bootstrapcdn

-0.52

 ब्रेकडाउन

-0.52

 Arboretum

-0.52

ValueStyle

-0.52

ouncements

-0.50

 arcs

-0.50

Дереккөздер

-0.50

POSITIVE LOGITS

 present

1.31

Present

1.14

present

1.13

 Present

1.13

 current

1.05

 PRESENT

0.99

 prefent

0.96

 présent

0.95

current

0.94

 Current

0.94

Activations Density 0.265%

references to inventions or presentations of new concepts and findings

No Comments

No Known Activations

references to inventions or presentations of new concepts and findings

No Comments

No Known Activations