INDEX

Explanations

references to specific aspects or features of various topics or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

OGND

-0.42

 Wikimedijinoj

-0.42

 vermelhas

-0.37

 shoes

-0.36

 الرخصة

-0.35

 book

-0.34

 noDo

-0.33

 institutions

-0.33

 number

-0.33

 devices

-0.32

POSITIVE LOGITS

 aspect

1.30

 aspects

1.30

aspects

1.29

 Aspects

1.26

Aspects

1.20

aspect

1.18

 Aspect

1.13

 aspek

1.07

Aspect

1.01

 aspectos

0.96

Activations Density 0.240%

references to specific aspects or features of various topics or subjects

No Comments

No Known Activations