INDEX

Explanations

references to notable individuals and events in entertainment and media

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

appearing before citations or examples

np_acts-logits-general · gemini-2.0-flash

proper nouns or specific names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 calendriers

-0.84

Carriera

-0.77

 >=",

-0.76

 kasarigan

-0.76

 الرياضيه

-0.71

 typelib

-0.71

 Bourgoin

-0.71

 AssemblyProduct

-0.69

Datuak

-0.69

 Hemisphere

-0.67

POSITIVE LOGITS

fortawesome

0.53

 respectivement

0.48

testens

0.48

 ciasc

0.48

 telles

0.47

 bijvoorbeeld

0.46

'{@

0.46

 tels

0.45

 Händen

0.45

XmlAccessorType

0.45

Activations Density 0.880%

references to notable individuals and events in entertainment and media

appearing before citations or examples

proper nouns or specific names

No Comments

No Known Activations