INDEX

Explanations

references to legal cases or citations

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

court citations and page numbers

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

出版年

-0.67

 kaarangay

-0.65

ImageContext

-0.62

 disambiguazione

-0.61

 utafitiHapana

-0.60

цездатний

-0.59

RenderAtEndOf

-0.59

\{\\

-0.57

Попис

-0.57

 فريبيس

-0.56

POSITIVE LOGITS

 finir

0.35

 Hügel

0.34

 keskus

0.34

AppCompat

0.33

imeni

0.33

 Lieberman

0.33

 ciudadanía

0.32

 Hoffmann

0.31

 MUNICIP

0.31

 Ferner

0.30

Activations Density 0.005%

references to legal cases or citations

court citations and page numbers

No Comments

No Known Activations