INDEX

Explanations

variations of the prefix "ex-"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

mobileqq

-0.79

ppelin

-0.79

ANDUM

-0.76

 numberOfRows

-0.73

 فريبيس

-0.73

 useParams

-0.72

forName

-0.72

ROLS

-0.71

tagHelper

-0.70

 useRouter

-0.70

POSITIVE LOGITS

ex

1.16

Ex

1.08

EX

1.08

EX

1.08

Ex

1.03

 EXCHANGE

1.03

 Exchange

1.02

 Exchanges

0.99

ex

0.98

 exchanges

0.97

Activations Density 0.202%

variations of the prefix "ex-"

No Comments

No Known Activations