INDEX

Explanations

words related to health, physical sensation, and maintenance

oai_token-act-pair · gemini-2.0-flash

generic text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ValueStyle

-0.98

DockStyle

-0.97

RenderAtEndOf

-0.69

liefert

-0.65

InjectAttribute

-0.65

 createState

-0.64

ExtendWith

-0.63

 ivelany

-0.62

principalColumn

-0.61

Cyfarwyddwr

-0.60

POSITIVE LOGITS

 firm

0.50

ⓧ

0.49

tinyos

0.49

pur

0.46

доми

0.45

in

0.44

 master

0.44

 well

0.43

 stock

0.42

 closed

0.42

Activations Density 1.728%

words related to health, physical sensation, and maintenance

generic text

No Comments

No Known Activations