INDEX

Explanations

terms related to the introduction or implementation of new concepts or changes

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

RenderAtEndOf

-0.56

EDEFAULT

-0.55

HtmlAttribute

-0.55

IVEREF

-0.50

 pinulongan

-0.47

introduction

-0.46

httphttps

-0.46

introduce

-0.46

 introduce

-0.44

 introduction

-0.43

POSITIVE LOGITS

Източници

0.46

 Gestão

0.42

Erreferentziak

0.41

 Públicas

0.39

 Trost

0.37

 Eltern

0.36

esModule

0.36

 Comunicação

0.36

 Stärke

0.36

angal

0.36

Activations Density 0.004%

terms related to the introduction or implementation of new concepts or changes

No Comments

No Known Activations