INDEX

Explanations

words related to personal relationships, companionship, or pet ownership.

oai_token-act-pair · gemini-2.0-flash

pets and dogs

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

 Freien

-0.58

WriteTagHelper

-0.54

 بيها

-0.52

 inversely

-0.51

قایناقلار

-0.50

 StatefulWidget

-0.50

UAGES

-0.47

 Mandate

-0.47

UTERS

-0.47

حياته

-0.47

POSITIVE LOGITS

 dogs

1.58

dog

1.43

 pets

1.41

 cats

1.33

 Dogs

1.29

 animals

1.23

Dogs

1.23

cat

1.23

dogs

1.21

pet

1.20

Activations Density 3.985%

words related to personal relationships, companionship, or pet ownership.

pets and dogs

No Comments

No Known Activations