INDEX

Explanations

geographic and location-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 pageContext

-0.65

 Clown

-0.53

 Laub

-0.48

UserScript

-0.48

 fieldNum

-0.48

textLabel

-0.47

Alb

-0.47

)))),

-0.47

__::

-0.47

astify

-0.47

POSITIVE LOGITS

 bookId

0.60

Skye

0.53

farin

0.52

 Skye

0.52

 Moab

0.51

 FormsModule

0.51

 Enix

0.50

 mCurrent

0.50

Wyoming

0.49

DotNetBar

0.49

Activations Density 1.347%

geographic and location-related terms

No Comments

No Known Activations