INDEX

Explanations

initialization indicators in programming contexts

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

programming language constructs and syntax elements

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

Questions and different languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

]='\

-0.68

-0.65

Interop

-0.53

λικ

-0.52

Erstellt

-0.52

olarmente

-0.51

++]=

-0.50

AndEndTag

-0.50

</caption>

-0.49

 numberOfRows

-0.47

POSITIVE LOGITS

 مرئيه

0.58

Referanser

0.55

 يتيمه

0.55

########.

0.54

 schuldig

0.54

 ویکی‌پدیا

0.54

 Kemen

0.54

 linkovi

0.53

dedores

0.52

itinéraire

0.52

Activations Density 0.022%

initialization indicators in programming contexts

programming language constructs and syntax elements

Questions and different languages

No Comments

No Known Activations