INDEX

Explanations

code snippets or syntactical structures related to programming

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

Code or special characters

np_acts-logits-general · gemini-2.0-flash

code structure and keywords

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

 Gilmore

-0.59

inosi

-0.57

orteur

-0.57

енча

-0.54

findpost

-0.52

Демографія

-0.52

ofire

-0.51

delaire

-0.51

canestro

-0.49

 szolg

-0.49

POSITIVE LOGITS

 endwhile

0.63

 bezeichneter

0.58

}},\

0.54

unhofer

0.53

WEBPACK

0.49

 سكانية

0.48

endwhile

0.47

/>\

0.46

/*

0.46

:✨

0.46

Activations Density 0.127%

code snippets or syntactical structures related to programming

Code or special characters

code structure and keywords

No Comments

No Known Activations