INDEX

Explanations

words associated with agreements and compliance

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

before names or numbers

np_acts-logits-general · gemini-2.0-flash

Max Barry, give a, two statistical

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

findpost

-0.50

urlencoded

-0.47

nextProps

-0.44

localctx

-0.43

 buka

-0.41

JoinColumn

-0.41

 Quais

-0.40

 fala

-0.40

 acima

-0.39

WidgetItem

-0.39

POSITIVE LOGITS

حياتها

0.69

 ویکی‌پدیا

0.69

uxxxx

0.67

Portail

0.66

)$_

0.64

:✨

0.63

esez

0.62

Va

0.61

 milo

0.61

 propOrder

0.60

Activations Density 0.038%

words associated with agreements and compliance

before names or numbers

Max Barry, give a, two statistical

No Comments

No Known Activations