INDEX

Explanations

words indicating affection or strong preference for something

oai_token-act-pair · gemini-2.0-flash

all

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OGND

-0.81

 surla

-0.71

期刊论文

-0.70

enumii

-0.68

waitKey

-0.68

windowFixed

-0.63

 aapt

-0.63

,:]

-0.62

UpInside

-0.61

ĝis

-0.60

POSITIVE LOGITS

 everything

1.77

everything

1.59

Everything

1.45

 Everything

1.44

 things

1.37

 anything

1.27

 allt

1.24

 alles

1.23

 tudo

1.23

 EVERYTHING

1.20

Activations Density 1.382%

words indicating affection or strong preference for something

all

No Comments

No Known Activations