INDEX

Explanations

words and phrases related to unity

oai_token-act-pair · gemini-2.0-flash

unity

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

rungsseite

-0.91

ConstraintMaker

-0.79

DockStyle

-0.74

PerformLayout

-0.73

omock

-0.73

 surla

-0.70

MIDDLEWARE

-0.69

enderror

-0.69

 GenerationType

-0.68

 informée

-0.68

POSITIVE LOGITS

one

0.70

 Einheit

0.53

 together

0.48

One

0.46

ONE

0.45

one

0.44

One

0.44

 LUMP

0.44

 одной

0.44

 unum

0.43

Activations Density 0.981%

words and phrases related to unity

unity

No Comments

No Known Activations