INDEX

Explanations

references to programming or namespace declarations

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

namespace or assume

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

-0.25

↵

-0.25

mysqli

-0.23

 Bodies

-0.23

-0.22

“

-0.21

wicket

-0.20

########.

-0.20

 télécommande

-0.20

 alın

-0.19

POSITIVE LOGITS

出版年

0.81

帖最后由

0.80

ArgsConstructor

0.79

 ſeinen

0.75

تقاوى

0.75

 الرياضيه

0.74

RectangleBorder

0.73

 AssemblyTitle

0.73

niſſe

0.73

 ſeinem

0.73

Activations Density 0.001%

references to programming or namespace declarations

namespace or assume

No Comments

No Known Activations