INDEX

Explanations

code snippets or examples, especially those involving matrixes, classes, algorithms, reports, problems and functions.

oai_token-act-pair · gemini-2.0-flash

"following" in different languages

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

JoinTable

-0.50

putBoolean

-0.47

ftagPool

-0.44

ávat

-0.43

buh

-0.42

 Regie

-0.41

gebir

-0.40

ėjimas

-0.40

getIntent

-0.40

Dichloroethane

-0.40

POSITIVE LOGITS

 following

1.82

following

1.73

 Following

1.57

 siguiente

1.54

 seguinte

1.53

Following

1.51

 suivantes

1.51

 следующее

1.48

 suivants

1.48

 FOLLOWING

1.48

Activations Density 6.895%

code snippets or examples, especially those involving matrixes, classes, algorithms, reports, problems and functions.

"following" in different languages

No Comments

No Known Activations