INDEX

Explanations

references to cursor properties in coding or programming contexts

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

cursor and execute

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

 وتسجيلات

-0.40

EOUT

-0.34

formazioni

-0.33

 valsty

-0.32

bringen

-0.32

jelent

-0.31

 laiko

-0.31

 hoş

-0.31

yyj

-0.31

 nust

-0.30

POSITIVE LOGITS

cursor

2.20

 cursor

1.51

 Cursor

1.37

Cursor

1.37

CURSOR

1.29

Cursors

1.25

cursors

1.23

ursor

0.98

setCursor

0.93

 curs

0.91

Activations Density 0.002%

references to cursor properties in coding or programming contexts

cursor and execute

No Comments

No Known Activations