INDEX

Explanations

mathematical symbols and expressions related to mathematical structures or equations

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

programming notation and special characters

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

 AssemblyCulture

-0.41

MigrationBuilder

-0.39

Ƚ

-0.37

 Auft

-0.35

 them

-0.35

 IMPRO

-0.33

 препратки

-0.33

Przypisy

-0.33

 potential

-0.33

 Svensson

-0.33

POSITIVE LOGITS

 disambiguazione

0.77

tagHelperRunner

0.72



0.59

RUnlock

0.57

 ExecuteAsync

0.57

SharedDtor

0.57

verwijspagina

0.55

 يتيمه

0.53

 nakalista

0.52

yarnpkg

0.50

Activations Density 0.177%

mathematical symbols and expressions related to mathematical structures or equations

programming notation and special characters

No Comments

No Known Activations