INDEX

Explanations

programming constructs and keywords associated with memory allocation and initialization in code

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

accessing second element of pair

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 betweenstory

-0.70

addPreferredGap

-0.57

 BrowserModule

-0.54

 AssemblyTitle

-0.53

 vectorielle

-0.53

adaptiveStyles

-0.52

tagHelperRunner

-0.51

addGap

-0.49

EditorBrowsable

-0.49

bootstrapcdn

-0.48

POSITIVE LOGITS

setupUi

0.54

thâu

0.50

omitempty

0.50

Upgradeable

0.49

EndInit

0.49

soever

0.49

nativeElement

0.49

 Wikimedijinoj

0.48

finch

0.48

keteers

0.48

Activations Density 0.017%

programming constructs and keywords associated with memory allocation and initialization in code

accessing second element of pair

No Comments

No Known Activations