INDEX

Explanations

mathematical expressions and notations related to linear transformations and their properties

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

PMailer

-0.73

nodoc

-0.73

parsedMessage

-0.71

+#+#

-0.70

oneofs

-0.68

awtextra

-0.68

 pinulongan

-0.66

ſehen

-0.66

 defaultstate

-0.65

 GenerationType

-0.65

POSITIVE LOGITS

 navideño

0.34

 Italij

0.33

 navideña

0.32

jaciół

0.32

ItemSelected

0.31

 nocturno

0.30

 corrientes

0.30

faatkan

0.30

 Fußballspieler

0.30

 Münster

0.29

Activations Density 0.068%

mathematical expressions and notations related to linear transformations and their properties

No Comments

No Known Activations