INDEX

Explanations

programming constructs related to function definitions and their annotations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Code-related tokens/words

np_acts-logits-general · gemini-2.0-flash

conditional logic or code blocks

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

HtmlAttribute

-0.61

\{\\

-0.58

sidemargin

-0.56

</table>

-0.55

 AssemblyCompany

-0.53

BufferException

-0.53

featureID

-0.52

adə

-0.52

imetric

-0.52

 daarbij

-0.51

POSITIVE LOGITS

'${

0.71

widget

0.70

 Future

0.68

 widget

0.67

Widgets

0.66

Future

0.65

Widget

0.64

Cubit

0.63

flutter

0.61

controller

0.61

Activations Density 0.111%

programming constructs related to function definitions and their annotations

Code-related tokens/words

conditional logic or code blocks

No Comments

No Known Activations