INDEX

Explanations

mathematical terms and symbols related to analysis and error measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

StoryboardSegue

-0.65

Hentet

-0.50

 BoxFit

-0.47

 defaultstate

-0.39

 herido

-0.36

makeConstraints

-0.36

Numerade

-0.34

 calorías

-0.34

":[{

-0.33

addContainerGap

-0.33

POSITIVE LOGITS

SequentialGroup

0.65

XtraReports

0.52

Espèce

0.51

 لينك

0.49

Jeografia

0.47

 Precise

0.45

 CHAMP

0.44

COUVER

0.43

belo

0.43

edd

0.43

Activations Density 1.481%

mathematical terms and symbols related to analysis and error measurement

No Comments

No Known Activations