INDEX

Explanations

code structures and syntax indicative of programming or technical documentation

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

Code, compiler, or programming related syntax

np_acts-logits-general · gemini-2.0-flash

category:divers

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

 AssemblyCulture

-1.05

}$.\\

-0.87

__':

-0.86

AndEndTag

-0.84

});*/

-0.83

-0.81

}*/

-0.80

*/

-0.80

msgSender

-0.79

 defaultstate

-0.76

POSITIVE LOGITS

 ostavi

0.48

 Cholera

0.46

ricos

0.40

ithin

0.40

 tendência

0.40

isons

0.40

mados

0.39

backtracking

0.39

 catég

0.38

Terug

0.38

Activations Density 0.077%

code structures and syntax indicative of programming or technical documentation

Code, compiler, or programming related syntax

category:divers

No Comments

No Known Activations