INDEX

Explanations

terms and concepts related to different scientific phenomena and processes

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

preceding "limit", "one", "DR", "species", or "wheelchair"

np_acts-logits-general · gemini-2.0-flash

wheelchair accessible

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 myſelf

-0.67

razos

-0.64

 iſt

-0.63

abundance

-0.63

iries

-0.63

lidene

-0.62

Carrière

-0.61

levance

-0.61

 ostavi

-0.61

 Jefus

-0.61

POSITIVE LOGITS

Hentet

0.91

 étrangères

0.55

 Abonnez

0.55

routeProvider

0.55

 متعلقه

0.54

 culturelles

0.54

UnitTesting

0.54

Parcelize

0.49

 henvisninger

0.48

 kiin

0.48

Activations Density 0.579%

terms and concepts related to different scientific phenomena and processes

preceding "limit", "one", "DR", "species", or "wheelchair"

wheelchair accessible

No Comments

No Known Activations