INDEX

Explanations

phrases that highlight variety and inclusivity in options or experiences

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

after numbers

np_acts-logits-general · gemini-2.0-flash

blood serum

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

 nakalista

-0.74

 autorytatywna

-0.67

ταν

-0.61

ConverterFactory

-0.58

Parcelize

-0.57

GEBURTSDATUM

-0.57

 transférez

-0.56

XmlAccessType

-0.54

AlterField

-0.54

 surla

-0.54

POSITIVE LOGITS

 something

1.34

Something

1.17

something

1.17

 Something

1.11

 SOMETHING

0.91

 något

0.86

 caters

0.86

 coś

0.86

 somethin

0.83

 cater

0.82

Activations Density 0.114%

phrases that highlight variety and inclusivity in options or experiences

after numbers

blood serum

No Comments

No Known Activations