INDEX

Explanations

words related to organizations and institutions

oai_token-act-pair · gemini-2.0-flash

organizations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

LogManager

-0.53

 medlems

-0.49

igny

-0.49

ριά

-0.46

+:+

-0.46

 médicaux

-0.45

OUNT

-0.45

cyd

-0.45

 toppen

-0.44

 dió

-0.43

POSITIVE LOGITS

 committed

1.69

 dedicated

1.62

dedicated

1.52

committed

1.39

 Committed

1.33

 Dedicated

1.28

Dedicated

1.27

 devoted

1.20

 dedicate

1.19

Committed

1.19

Activations Density 2.545%

words related to organizations and institutions

organizations

No Comments

No Known Activations