INDEX

Explanations

structured data and numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ecm

-0.54

er

-0.49

saraba

-0.46

 Münster

-0.46

闪过

-0.45

rdoba

-0.44

zda

-0.43

anyol

-0.43

Les

-0.42

Fixed

-0.42

POSITIVE LOGITS

IsContent

0.93

AndroidJUnit

0.82

rungsseite

0.82

RegressionTest

0.81

verticalLayout

0.81

 MenuView

0.81

getMenuInflater

0.80

 StatelessWidget

0.80

parsedMessage

0.78

 otomatig

0.78

Activations Density 0.390%

structured data and numerical values

No Comments

No Known Activations