INDEX

Explanations

references or indications of edits and updates in text

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

Characters or symbols following numbers

np_acts-logits-general · gemini-2.0-flash

fluorescent lamp or commander

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

 utafitiHapana

-0.65

Ārējās

-0.60

 cref

-0.57

 permitan

-0.52

 uLocal

-0.49

Referencias

-0.49

ChildScrollView

-0.48

سمبر

-0.46

ObjectModel

-0.46

Externí

-0.46

POSITIVE LOGITS

 ISNI

0.65

handleRequest

0.56

Искәрмәләр

0.53

jooq

0.53

sizeCache

0.52

 Cham

0.51

onomia

0.50

EndGlobalSection

0.49

.*")]

0.48

ball

0.48

Activations Density 0.032%

references or indications of edits and updates in text

Characters or symbols following numbers

fluorescent lamp or commander

No Comments

No Known Activations