INDEX

Explanations

punctuation marks and formatting in text

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

IsMutable

-0.83

دانشنامهٔ

-0.81

setVerticalGroup

-0.78

 kasarigan

-0.77

adaptiveStyles

-0.76

ftagPool

-0.76

richTextPanel

-0.74

/**

-0.74

httphttps

-0.73

AddTagHelper

-0.72

POSITIVE LOGITS

te

0.29

0.28

pre

0.28

ha

0.28

ho

0.27

²

0.27

goto

0.26

{}

0.26

Safe

0.26

 said

0.25

Activations Density 0.009%

punctuation marks and formatting in text

No Comments

No Known Activations