INDEX

Explanations

words that represent various script or language characters, particularly in non-Latin scripts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

```

-0.55

 injust

-0.54

 nutz

-0.53

 intre

-0.53

 Gabel

-0.53

ում

-0.53

 geste

-0.52

 lenker

-0.52

for

-0.52

icher

-0.52

POSITIVE LOGITS

 تانيه

0.86

NewLabel

0.84

ghijklmnop

0.83

 Мексичка

0.79

enumii

0.73

NUMX

0.72

0.70

holdet

0.69

DoubleQuotes

0.68

wapV

0.67

Activations Density 0.132%

words that represent various script or language characters, particularly in non-Latin scripts

No Comments

No Known Activations