INDEX

Explanations

programming-related terminology and function definitions

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

Code or pseudocode that includes the word "return"

np_acts-logits-general · gemini-2.0-flash

returns values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

 ModelExpression

-0.46

TagMode

-0.42

 iprot

-0.42

 onCreate

-0.42

nement

-0.42

Werdegang

-0.41

amentlich

-0.41

AddTagHelper

-0.41

IsUnicode

-0.40

Diweddarwch

-0.40

POSITIVE LOGITS

 return

2.34

 returns

2.03

 Return

2.00

 returned

1.97

 returning

1.91

 RETURN

1.87

Return

1.80

return

1.70

 Returns

1.68

 retorno

1.64

Activations Density 0.694%

programming-related terminology and function definitions

Code or pseudocode that includes the word "return"

returns values

No Comments

No Known Activations