INDEX

Explanations

terms related to magnetic properties and coding syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

zake

-0.47

 itſelf

-0.46

 Utica

-0.46

 Jefus

-0.45

GOTREF

-0.43

 régal

-0.43

 excite

-0.42

zas

-0.42

 Chriſt

-0.41

hões

-0.41

POSITIVE LOGITS

RegressionTest

1.01

__':

0.99

 iParam

0.95

存于互联网档案馆

0.81

PreferredItem

0.80

ArrowToggle

0.79

 Савезне

0.78

SourceChecksum

0.78

 AssemblyTitle

0.77

__":

0.77

Activations Density 0.040%

terms related to magnetic properties and coding syntax

No Comments

No Known Activations