INDEX

Explanations

punctuation and script-related syntax elements

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

end of code statement

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

 autorytatywna

-0.82

migrationBuilder

-0.80

Autoritní

-0.64

 مشين

-0.60

+#+#

-0.60

Билгалдахарш

-0.57

LLocation

-0.57

참고

-0.56

 GenerationType

-0.56

parsedMessage

-0.56

POSITIVE LOGITS

 AttributeSet

0.41

OrNil

0.37

 لينك

0.30

 Autorisations

0.30

ゴン

0.29

UrlEncoded

0.29

DoubleQuotes

0.29

Ṛ

0.28

 drums

0.28

bin

0.28

Activations Density 0.051%

punctuation and script-related syntax elements

end of code statement

No Comments

No Known Activations