INDEX

Explanations

words that begin with the prefix "und"

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

"Und" or "Sund" followed by another token

np_acts-logits-general · gemini-2.0-flash

undaria and undoped

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

er

-0.73

queryInterface

-0.56

zzleHttp

-0.55

GrantedAuthority

-0.49

 works

-0.47

 MenuView

-0.47

 сорта

-0.47

 Team

-0.46

 diret

-0.46

forward

-0.46

POSITIVE LOGITS

amental

0.71

 Мексичка

0.69

 surla

0.66

amentals

0.66

 الحره

0.64

 ddelweddau

0.63

 Савезне

0.62

ReusableCell

0.61

 NUKAT

0.60

 CreateTagHelper

0.60

Activations Density 0.122%

words that begin with the prefix "und"

"Und" or "Sund" followed by another token

undaria and undoped

No Comments

No Known Activations