INDEX

Explanations

phrases that express questions or inquiries regarding actions, capabilities, and circumstances

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

 carica

-0.45

Closer

-0.44

 annuel

-0.44

Palmar

-0.44

tigem

-0.43

 actifs

-0.43

 dirilis

-0.43

 Mexique

-0.42

 chì

-0.42

 női

-0.42

POSITIVE LOGITS

GEBURTSDATUM

0.81

 NSCoder

0.68

 StatelessWidget

0.68

AnchorStyles

0.63

 sleeved

0.63

 jScrollPane

0.62

 StatefulWidget

0.62

 CreateTagHelper

0.61

 Cataloging

0.60

mergeFrom

0.60

Activations Density 0.225%

phrases that express questions or inquiries regarding actions, capabilities, and circumstances

No Comments

No Known Activations