INDEX

Explanations

return statements in code

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

Code snippets returning a value

np_acts-logits-general · gemini-2.0-flash

`return` followed by code or specific words

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 yatak

-0.46

 πρά

-0.41

 statunitense

-0.41

しき

-0.40

too

-0.40

écart

-0.39

calloc

-0.39

ksessa

-0.39

влении

-0.39

connection

-0.38

POSITIVE LOGITS

ValueStyle

1.23

IsContent

1.04

 <=",

0.95

تقاوى

0.91

 AssemblyCulture

0.89

parsedMessage

0.89

RenderAtEndOf

0.88

)"),

0.87

 مشين

0.85

OGND

0.85

Activations Density 0.047%

return statements in code

Code snippets returning a value

`return` followed by code or specific words

No Comments

No Known Activations