INDEX

Explanations

references to awards and recognitions in the context of creative works

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

mentions of prestigious awards and recognition

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

Nobel prize winners and awards

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

Personensuche

-0.71

aarrggbb

-0.64

">//

-0.62

 Biôgrafia

-0.61

COUVER

-0.58

ttino

-0.57

UnknownFieldSet

-0.57

تقاوى

-0.56

ANDUM

-0.56

 Disqus

-0.56

POSITIVE LOGITS

 award

2.71

 awards

2.55

 Award

2.45

 prize

2.25

Award

2.23

 Awards

2.22

 AWARD

2.20

award

2.19

 awarded

2.14

 winners

2.10

Activations Density 0.383%

references to awards and recognitions in the context of creative works

mentions of prestigious awards and recognition

Nobel prize winners and awards

No Comments

No Known Activations