INDEX

Explanations

sequences of whitespace or formatting characters

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

 поля

-0.38

líben

-0.34

 GenerationType

-0.33

 wyda

-0.32

Palmarès

-0.32

vne

-0.31

-0.30

 الميل

-0.29

 <>",

-0.29

TokenNameDOT

-0.29

POSITIVE LOGITS

httphttps

0.56

ScopeManager

0.56

Portale

0.55

ReusableCell

0.55

ſelf

0.54

 itſelf

0.54

numerusform

0.53

BagLayout

0.53

expandindo

0.52

 fubject

0.52

Activations Density 0.017%

sequences of whitespace or formatting characters

No Comments

No Known Activations