INDEX

Explanations

references to geographical locations and community organizations

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

Prepositions and punctuation

np_acts-logits-general · gemini-2.0-flash

Ontario locations and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Vancouver

-0.78

 nahilalakip

-0.74

Vancouver

-0.74

 Edmonton

-0.72

 Winnipeg

-0.66

 Calgary

-0.65

 Newfoundland

-0.65

 Manitoba

-0.64

Edmonton

-0.63

 Montreal

-0.61

POSITIVE LOGITS

KommentareTeilen

0.63

Tikang

0.57

Erreferentziak

0.55

antMatchers

0.54

 nakalista

0.53

 فريبيس

0.53

adoc

0.51

 CASO

0.49

########.

0.49

 Ather

0.48

Activations Density 0.072%

references to geographical locations and community organizations

Prepositions and punctuation

Ontario locations and entities

No Comments

No Known Activations