INDEX

Explanations

comments and annotations related to function definitions and parameters

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

Code comments containing the "@" symbol

np_acts-logits-general · gemini-2.0-flash

documentation tags like `@private`

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

<",

-0.47

 bờ

-0.47

 aimer

-0.45

 درب

-0.42

buff

-0.41

xtick

-0.40

/}.

-0.40

chkin

-0.40

пьютер

-0.39

ahn

-0.39

POSITIVE LOGITS

IntoConstraints

0.70

\{\\

0.69

 للمعارف

0.68

 дописавши

0.68

########.

0.66

 المعيارى

0.66

tvguidetime

0.65

Cyfeiriadau

0.64

MemoryWarning

0.63

endpush

0.63

Activations Density 0.073%

comments and annotations related to function definitions and parameters

Code comments containing the "@" symbol

documentation tags like `@private`

No Comments

No Known Activations