INDEX

Explanations

specific terms or symbols related to legislative or parliamentary context

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

Ku Li, Sai Shan, amsmath

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

 HasFactory

-0.41

-0.35

Statistiche

-0.32

 Еще

-0.32

val

-0.32

getActiveSheet

-0.31

dol

-0.30

 ду

-0.30

Nhi

-0.30

POSITIVE LOGITS

Jîn

0.70

oa̍t

0.67

Chham

0.65

ніципа

0.65

 chi̍t

0.63

+#+#

0.62

 Chwiliwch

0.60

AppMethodBeat

0.59

 Roskov

0.57

sī

0.57

Activations Density 0.000%

specific terms or symbols related to legislative or parliamentary context

Ku Li, Sai Shan, amsmath

No Comments

No Known Activations