INDEX

Explanations

comments or documentation in programming code

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

documentation style comments or annotations in programming code

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

code comments and notes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.20.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

 then

-0.62

 thereafter

-0.59

 infine

-0.57

 finally

-0.57

 наконец

-0.57

then

-0.56

finally

-0.55

now

-0.55

BagConstraints

-0.53

конец

-0.51

POSITIVE LOGITS

TODO

0.86

 TODO

0.83

 FIXME

0.83

 ویکی‌پدیا

0.82

 NOTE

0.80

NOTE

0.77

todo

0.75

 Note

0.70

 ReSharper

0.68

 todo

0.67

Activations Density 0.045%

comments or documentation in programming code

documentation style comments or annotations in programming code

code comments and notes

No Comments

No Known Activations