INDEX

Explanations

terms related to controls, adjustments, and operations of devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

DOCTYPE

-0.55

CP

-0.49

componentDid

-0.47

copia

-0.46

ந்த

-0.45

 mendes

-0.45

ZP

-0.45

 demands

-0.44

scape

-0.43

UK

-0.43

POSITIVE LOGITS

 defaultstate

0.88

 tartalomajánló

0.77

 мәкал

0.72

UnknownFields

0.71

 MainAxisSize

0.69

RenderAtEndOf

0.68

 dimming

0.65

 himo

0.65

DeleteBehavior

0.65

DrawerToggle

0.65

Activations Density 0.355%

terms related to controls, adjustments, and operations of devices

No Comments

No Known Activations