INDEX

Explanations

numerical values and references to data or categories typically associated with structured information

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

Geplaatst

-0.63

tagHelperRunner

-0.63

Vidite

-0.60

 otomatig

-0.57

SourceChecksum

-0.55

ValueStyle

-0.55

BagLayout

-0.55

 Roskov

-0.53

IVEREF

-0.53

 kaarangay

-0.52

POSITIVE LOGITS

hésite

0.33

hdashline

0.33

 NSCoder

0.32

isAuth

0.31

ட்ச

0.31

wość

0.31

 acreage

0.29

할

0.29

Roma

0.29

InjectAttribute

0.29

Activations Density 1.024%

numerical values and references to data or categories typically associated with structured information

No Comments

No Known Activations