INDEX

Explanations

code snippets related to virtual machines

oai_token-act-pair · gemini-2.0-flash

virtual machines

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

readObject

-0.55

GeneratedValue

-0.48

CONSULT

-0.47

testng

-0.46

Ground

-0.46

mlb

-0.45

 tape

-0.45

Peace

-0.45

 Ground

-0.45

 Peace

-0.45

POSITIVE LOGITS

 <=",

0.78

 препратки

0.75

Бахар

0.63

 himo

0.61

 Référence

0.59

OGND

0.57

__*/

0.57

EndInit

0.57

MENAFN

0.57

 estekak

0.54

Activations Density 1.541%

code snippets related to virtual machines

virtual machines

No Comments

No Known Activations