INDEX

Explanations

references to organizations and institutions related to health or academia

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

Follows capitalized words

np_acts-logits-general · gemini-2.0-flash

compound identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Geplaatst

-0.68

 calendriers

-0.63

initComponents

-0.61

 محفوظة

-0.60

 ostavi

-0.59

ignty

-0.59

 بيها

-0.59

 AssemblyCulture

-0.59

ViewInit

-0.59

Controllo

-0.58

POSITIVE LOGITS

grà

0.56

IonicModule

0.53

Бахар

0.51

arikat

0.49

примеча

0.48

RTDA

0.48

BASEPATH

0.47

 famí

0.47

 يتيمه

0.46

ฯ

0.46

Activations Density 1.013%

references to organizations and institutions related to health or academia

Follows capitalized words

compound identifiers

No Comments

No Known Activations