INDEX

Explanations

terms related to publishing and editorial processes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rungsseite

-0.68

adaptiveStyles

-0.68

dawnictwo

-0.54

 изда

-0.50

 Editions

-0.50

 AssemblyCulture

-0.47

EndProject

-0.47

fromnode

-0.47

 betweenstory

-0.46

 المعيارى

-0.46

POSITIVE LOGITS

SaveChangesAsync

0.43

PerformLayout

0.42

ForRow

0.41

 surla

0.40

GenerationType

0.38

+#+#

0.38

EndInit

0.37

 Besøkt

0.35

 sobres

0.35

subpackage

0.34

Activations Density 0.010%

terms related to publishing and editorial processes

No Comments

No Known Activations