INDEX

Explanations

function definitions and data structure manipulations within programming contexts

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

abestanden

-0.88

DoubleQuotes

-0.83

AsUp

-0.78

 myſelf

-0.77

Datuak

-0.77

IsMutable

-0.77

:✨

-0.76

تقاوى

-0.75

titleMargin

-0.75

erschutz

-0.74

POSITIVE LOGITS

</strong>

0.41

ungkap

0.41

</em>

0.40

0.39

or

0.39

ungkinkan

0.39

 understanding

0.37

 hoạt

0.37

 pantallas

0.37

withId

0.37

Activations Density 0.357%

function definitions and data structure manipulations within programming contexts

No Comments

No Known Activations