INDEX

Explanations

programming constructs related to control flow and loops

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

for loop condition

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

UrlResolution

-0.56

 related

-0.49

LayoutConstraint

-0.46

AsStream

-0.45

 associated

-0.45

 well

-0.45

PIER

-0.45

endpush

-0.45

 also

-0.44

fare

-0.44

POSITIVE LOGITS

 незавершена

0.41

fromnode

0.39

 ویکی‌پدی

0.38

AndEndTag

0.37

 exhibición

0.35

 numerus

0.35

Referințe

0.35

 podjela

0.35

ChildScrollView

0.34

hdashline

0.34

Activations Density 0.006%

programming constructs related to control flow and loops

for loop condition

No Comments

No Known Activations