INDEX

Explanations

return statements in code

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

code return values

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

+#+#

-0.52

Бахар

-0.49

fony

-0.45

rawDesc

-0.45

Portail

-0.44

djangoproject

-0.43

smithy

-0.42

randomUUID

-0.41

CCN

-0.40

OCD

-0.40

POSITIVE LOGITS

 return

1.94

 Return

1.52

 RETURN

1.46

Return

1.41

 returns

1.20

RETURN

1.16

 returning

1.11

 retour

1.09

 returned

1.08

 retorno

0.99

Activations Density 0.011%

return statements in code

code return values

No Comments

No Known Activations