INDEX

Explanations

scientific writing that contains the words "we", "compute" and "to" .

oai_token-act-pair · gemini-2.0-flash

to

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

 GenerationType

-1.03

GOTREF

-0.97

 EconPapers

-0.92

 виправивши

-0.90

 Italijanski

-0.88

 avoient

-0.80

 AssemblyCulture

-0.79

 faſt

-0.76

DropTable

-0.73

ConstraintMaker

-0.73

POSITIVE LOGITS

 estimate

0.57

for

0.51

 evaluate

0.48

is

0.46

in

0.46

 assess

0.45

 monitor

0.45

ř

0.44

/]

0.44

 monit

0.43

Activations Density 3.314%

scientific writing that contains the words "we", "compute" and "to" .

to

No Comments

No Known Activations