INDEX

Explanations

references to prestigious awards, particularly the Nobel Prize

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

Awards, prizes, and recognition

np_acts-logits-general · gemini-2.0-flash

award and prize names

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

aarrggbb

-0.80

Personensuche

-0.70

 Disqus

-0.64

UnknownFieldSet

-0.62

 tartalomajánló

-0.62

kuuta

-0.62

تقاوى

-0.60

 '\\;'

-0.60

">//

-0.60

IsPostBack

-0.60

POSITIVE LOGITS

 award

2.79

 Award

2.55

 awards

2.52

Award

2.30

 AWARD

2.26

award

2.26

 Awards

2.23

 awarded

2.20

Awards

2.08

 winner

2.03

Activations Density 0.372%

references to prestigious awards, particularly the Nobel Prize

Awards, prizes, and recognition

award and prize names

No Comments

No Known Activations