INDEX

Explanations

phrases indicating sources or origins of information or data

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

AddTagHelper

-0.75

MessageOf

-0.68

 nahilalakip

-0.65

uxxxx

-0.62

Tikang

-0.59

oneofs

-0.54

出版年

-0.54

expandindo

-0.52

msgTypes

-0.50

ViewImports

-0.50

POSITIVE LOGITS

NewLabel

0.34

ariki

0.30

 devriez

0.30

 kości

0.28

Offers

0.28

IBAction

0.28

 Chips

0.27

 chinoise

0.27

 kvinna

0.27

 Offers

0.27

Activations Density 0.006%

phrases indicating sources or origins of information or data

No Comments

No Known Activations

phrases indicating sources or origins of information or data

No Comments

No Known Activations