INDEX

Explanations

references to specific areas and regions, particularly in data analysis contexts

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

"area" followed by spatial or mathematical terms

np_acts-logits-general · gemini-2.0-flash

area under curve percentage

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

lihood

-0.63

ftagPool

-0.57

--}}

-0.55

 singoli

-0.54

 HasFactory

-0.54

zzar

-0.54

AutoField

-0.51

estacks

-0.51

🏻

-0.50

>--}}

-0.50

POSITIVE LOGITS

 AREA

0.90

 rugs

0.85

rug

0.83

 areas

0.82

 Areas

0.82

areas

0.81

 area

0.81

area

0.80

Areas

0.79

 Area

0.78

Activations Density 0.181%

references to specific areas and regions, particularly in data analysis contexts

"area" followed by spatial or mathematical terms

area under curve percentage

No Comments

No Known Activations