INDEX

Explanations

terms and phrases related to significance and importance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

einander

-0.62

toHaveBeenCalled

-0.55

myname

-0.53

 ucapnya

-0.53

تام

-0.52

ähig

-0.52

clf

-0.50

 officially

-0.49

ateľ

-0.49

ofür

-0.48

POSITIVE LOGITS

ukone

0.83

ValueStyle

0.74

URLException

0.73

 ویکی‌پدی

0.72

abestanden

0.70

 الاطلاع

0.67

yntaxException

0.60

tagHelperRunner

0.60

 للاسماء

0.58

IsContent

0.58

Activations Density 0.278%

terms and phrases related to significance and importance in various contexts

No Comments

No Known Activations