INDEX

Explanations

programming-related terms and classes used in various coding contexts

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 NSCoder

-0.68

 otomatig

-0.65

 '\\;'

-0.53

InstrumentedTest

-0.52

\{\\

-0.48

parsedMessage

-0.45

jsonwebtoken

-0.44

Ārējās

-0.44

 boom

-0.44

 Adel

-0.44

POSITIVE LOGITS

IntoConstraints

0.92

AnimationsModule

0.78

omock

0.63

DrawerToggle

0.56

TextWatcher

0.51

lapsingToolbar

0.50

prefixer

0.42

TagHelper

0.41

 BeautifulSoup

0.40

TypedArray

0.40

Activations Density 0.002%

programming-related terms and classes used in various coding contexts

No Comments

No Known Activations