INDEX

Explanations

elements related to numerical data or quantitative expressions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.hook_resid_post

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

ira

-0.48

ston

-0.43

By

-0.43

 passato

-0.42

 lack

-0.40

ben

-0.39

mek

-0.39

ado

-0.39

ses

-0.39

Ban

-0.39

POSITIVE LOGITS

DockStyle

1.02

oredCriteria

1.01

RegressionTest

1.01

ValueStyle

0.98

awtextra

0.93

0.91

脚注の使い方

0.88

addContainerGap

0.84

المناصب

0.84

FilterChain

0.83

Activations Density 0.001%

elements related to numerical data or quantitative expressions

No Comments

No Known Activations