INDEX

Explanations

programming terms related to function definitions and boolean logic

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

license terms and permissions

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

Aiheesta

-0.56

LookAnd

-0.54

 يتيمه

-0.53

 HasFactory

-0.50

 betweenstory

-0.49

protoimpl

-0.47

graphicx

-0.46

cjs

-0.46

 للمعارف

-0.45

MetaType

-0.44

POSITIVE LOGITS

IVEREF

0.66

setVerticalGroup

0.51

 CURLOPT

0.44

 verkle

0.43

MessageOf

0.43

 avanti

0.40

Ladies

0.40

bbq

0.40

WH

0.40

 rack

0.39

Activations Density 0.002%

programming terms related to function definitions and boolean logic

license terms and permissions

No Comments

No Known Activations