INDEX

Explanations

keywords and phrases related to religious or cultural concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 BorderRadius

-0.58

RegressionTest

-0.52

openqa

-0.50

xhtml

-0.49

Linq

-0.48

AnchorStyles

-0.48

 ddelweddau

-0.47

ėtų

-0.47

 utafitiHapana

-0.46

+#+

-0.45

POSITIVE LOGITS

Personendaten

0.75

Portail

0.63

 RemoteException

0.57

__(/*!

0.57

حياتها

0.56

Архівовано

0.56

 témoins

0.55

TestingModule

0.54

 lèvres

0.54

elemField

0.54

Activations Density 0.125%

keywords and phrases related to religious or cultural concepts

No Comments

No Known Activations