INDEX

Explanations

code-related patterns and elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Hozzáférés

-0.60

下载附件

-0.58

MethodManager

-0.56

owohl

-0.53

 mapStateToProps

-0.47

 soixante

-0.47

 braccia

-0.45

hynch

-0.45

ண்டும்

-0.44

 here

-0.43

POSITIVE LOGITS

DockStyle

0.91

OGND

0.76

 Pilate

0.74

setupUi

0.68

abestanden

0.62

0.59

KGB

0.58

 Byzantium

0.58

 Nicosia

0.58

Activations Density 1.382%

code-related patterns and elements

No Comments

No Known Activations