INDEX

Explanations

quantitative statistical comparisons and results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 فريبيس

-0.75

 שוליים

-0.67

 BoxFit

-0.63

__(/*!

-0.61

 tartalomajánló

-0.56

İstinadlar

-0.55

 ujednoznacz

-0.54

glLoad

-0.54

存于互联网档案馆

-0.52

DataAnnotations

-0.51

POSITIVE LOGITS

1.40

۰

1.03

０

0.88

০

0.76

۰

0.72

𝟎

0.64

 cero

0.56

 zéro

0.54

expandindo

0.48

 zero

0.47

Activations Density 1.021%

quantitative statistical comparisons and results

No Comments

No Known Activations