INDEX

Explanations

references to tests or test cases

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

awtextra

-0.83

 ModelExpression

-0.73

ReusableCell

-0.72

unknownFields

-0.69

IntoConstraints

-0.68

CppMethod

-0.67

 виправивши

-0.65

JoinColumn

-0.63

EDEFAULT

-0.63

ConstraintMaker

-0.62

POSITIVE LOGITS

Test

0.52

TestMethod

0.51

 turbidity

0.49

 Xunit

0.49

happened

0.48

ategorised

0.48

 Filip

0.47

 colours

0.46

 serra

0.46

 Arian

0.45

Activations Density 0.000%

references to tests or test cases

No Comments

No Known Activations