INDEX

Explanations

terms related to various computing concepts and tools

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

 noDo

-0.67

 CURIAM

-0.67

-------------</

-0.63

 cherchés

-0.63

########.

-0.61

 ffilmiau

-0.61

 referrerpolicy

-0.60

Diweddarwch

-0.57

 AspNetCore

-0.55

@"/

-0.55

POSITIVE LOGITS

 relativa

0.31

 ground

0.29

fag

0.28

 requerido

0.28

 cabina

0.27

TextBoxColumn

0.26

 mixte

0.25

Rè

0.25

 requerida

0.25

 Tuesday

0.25

Activations Density 0.024%

terms related to various computing concepts and tools

No Comments

No Known Activations