INDEX

Explanations

topics related to programming and technical explanations

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

the beginning of a new document or message

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

mathematical and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.20.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

oa̍t

-0.55

RegistryLite

-0.53

Халык

-0.52

Хьажоргаш

-0.52

 кӀ

-0.51

QMetaType

-0.51

сшта

-0.50

олові

-0.46

AfterClass

-0.45

pēc

-0.44

POSITIVE LOGITS

enumi

0.87

EnableWeb

0.78

-------

0.69

 AppColors

0.68

IZACIÓN

0.64

 nakalista

0.63

 LEYENDO

0.63

 wikipagina

0.62

ADVERTISEMENT

0.61

 برانيه

0.61

Activations Density 0.001%

topics related to programming and technical explanations

the beginning of a new document or message

mathematical and technical terms

No Comments

No Known Activations