INDEX

Explanations

definitions of classes and their attributes or methods in programming code

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

programming keywords and declarations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

rungsseite

-0.66

jspb

-0.65

#+#

-0.65

SharedCtor

-0.63

awtextra

-0.63

GEBURTSDATUM

-0.62

 виправивши

-0.61

 BytesLike

-0.59

verifyException

-0.57

 typelib

-0.56

POSITIVE LOGITS

RTLI

0.50

󠁬

0.34

 Зак

0.34

Портал

0.32

 Salerno

0.31

 enfans

0.31

 участок

0.30

 uska

0.30

 revient

0.29

wohner

0.29

Activations Density 0.008%

definitions of classes and their attributes or methods in programming code

programming keywords and declarations

No Comments

No Known Activations