INDEX

Explanations

phrases that indicate naming or defining something

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

introducing names or designations

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

 boyunca

-0.36

ISES

-0.34

 בלי

-0.34

andten

-0.33

Dichloropropene

-0.32

 portions

-0.32

 mäng

-0.31

 Paglinawan

-0.31

 izdel

-0.30

ješ

-0.30

POSITIVE LOGITS

 disambiguazione

0.67

Vidite

0.63

 AssemblyTitle

0.63

providedIn

0.63

]")]

0.62

 Италијани

0.62

UnknownFieldSet

0.61

 utafitiHapana

0.61

 pinulongan

0.61

Datuak

0.59

Activations Density 0.022%

phrases that indicate naming or defining something

introducing names or designations

No Comments

No Known Activations