INDEX

Explanations

return statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 propOrder

-0.95

'{@

-0.66

 الرياضيه

-0.66

 Ause

-0.65

WebElementEntity

-0.65

ⓧ

-0.62

bernador

-0.61

 onAnimation

-0.61

GraphicsUnit

-0.58

routeProvider

-0.58

POSITIVE LOGITS

ếc

0.53

centralwidget

0.48

Meik

0.48

rawDesc

0.47

slideUp

0.44

 fibrillation

0.43

RectangleBorder

0.43

dbach

0.43

ruti

0.43

SceneManagement

0.42

Activations Density 0.061%

return statements in code

No Comments

No Known Activations