INDEX

Explanations

terms related to programming constructs and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.61

ymas

-0.51

 září

-0.49

 noiembrie

-0.48

ñores

-0.46

aryti

-0.46

 Divulgação

-0.46

 uſed

-0.46

 worshipped

-0.45

ulgação

-0.44

POSITIVE LOGITS

ReusableCell

0.87

 StatefulWidget

0.85

شهاد

0.78

 AssemblyCulture

0.75

MemoryWarning

0.75

 AssemblyVersion

0.74

 مشين

0.74

 disambiguazione

0.73

 nahilalakip

0.71

Tikang

0.70

Activations Density 0.004%

terms related to programming constructs and documentation

No Comments

No Known Activations