INDEX

Explanations

numeric values or indicators associated with iterations or loops

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

=”

-0.47

 Proc

-0.47

LookAnd

-0.45

て

-0.44

 الا

-0.44

Obra

-0.43

 Roskov

-0.43

wa

-0.42

)}>

-0.42

POSITIVE LOGITS

VersionUID

0.89

AxisAlignment

0.87

HtmlAttribute

0.86

IntoConstraints

0.82

 Constitucional

0.77

ReusableCell

0.71

enumii

0.69

 NSCoder

0.68

 defaultstate

0.67

instancetype

0.65

Activations Density 0.070%

numeric values or indicators associated with iterations or loops

No Comments

No Known Activations