INDEX

Explanations

parameters and attributes related to programming, specifically in the context of data structures and methods

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

Code-related terms

np_acts-logits-general · gemini-2.0-flash

variable or property assignments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

and

-0.96

Lähteet

-0.83

principalColumn

-0.82

Jegyzetek

-0.78

WebElementEntity

-0.78

人和

-0.73

性和

-0.73

 lenker

-0.72

Weblinks

-0.72

ですし

-0.72

POSITIVE LOGITS

 sekal

0.60

 sebagainya

0.58

:''

0.55

дарь

0.55

leyebilirsiniz

0.54

 terceiros

0.52

 település

0.52

:""

0.52

 afterwards

0.51

}?>

0.51

Activations Density 0.346%

parameters and attributes related to programming, specifically in the context of data structures and methods

Code-related terms

variable or property assignments

No Comments

No Known Activations