INDEX

Explanations

words related to the arts and entertainment, especially theater and film

oai_token-act-pair · gemini-2.0-flash

form

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

AsUp

-0.74

posedge

-0.64

 OFDb

-0.55

borderSide

-0.55

setVerticalGroup

-0.55

 ISNI

-0.54

Carriera

-0.54

Cordialement

-0.54

eterangan

-0.53

 EdgeInsets

-0.52

POSITIVE LOGITS

 form

1.73

 Form

1.55

Form

1.52

form

1.48

 FORM

1.37

 forms

1.29

FORM

1.24

 Forms

1.16

forms

1.13

FORMS

1.07

Activations Density 1.523%

words related to the arts and entertainment, especially theater and film

form

No Comments

No Known Activations