INDEX

Explanations

code snippets explaining how something is being used in a program, or in legal language, where some numbered clause provides, in relevant part, or where the last paragraph of some article ran.

oai_token-act-pair · gemini-2.0-flash

legal/technical documents

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 createState

-0.69

StoryboardSegue

-0.60

ArrowToggle

-0.60

 Autorisations

-0.58

 GeoNames

-0.58

 WebDriverWait

-0.57

 onAnimation

-0.57

lwjgl

-0.57

 Infórmanos

-0.56

audiovisuel

-0.55

POSITIVE LOGITS

 grun

0.50

SizeF

0.49

 honnête

0.49

STOP

0.49

់

0.48

//

0.47

gawa

0.47

bunda

0.46

 STOP

0.46

 Stop

0.45

Activations Density 2.940%

code snippets explaining how something is being used in a program, or in legal language, where some numbered clause provides, in relevant part, or where the last paragraph of some article ran.

legal/technical documents

No Comments

No Known Activations