INDEX

Explanations

mentions of a specific programming library or framework

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

elle::, de.peeeq., iClarified, BOOST_MPL

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

󠁢

-0.50

toprule

-0.39

 equivalent

-0.39

équi

-0.37

 Equivalent

-0.36

 chance

-0.35

equivalent

-0.35

擦

-0.34

 colspan

-0.34

 thank

-0.33

POSITIVE LOGITS

webElementGuid

0.76

 CreateTagHelper

0.73

uxxxx

0.72

 CanadaChoose

0.69

hoeddwyd

0.66

-------

0.65

IndentedString

0.63

انيف

0.63

 مشين

0.62

 beginnetje

0.62

Activations Density 0.012%

mentions of a specific programming library or framework

elle::, de.peeeq., iClarified, BOOST_MPL

No Comments

No Known Activations