INDEX

Explanations

programming structures and syntax elements, particularly those related to loops and conditionals

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

Code that includes loop indices

np_acts-logits-general · gemini-2.0-flash

loop counters and code structure

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Bioaccumulative

-0.47

 femininos

-0.47

 zijne

-0.46

 devenus

-0.46

 mijne

-0.44

 godk

-0.43

 techniczne

-0.40

oarece

-0.40

economia

-0.40

MENAFN

-0.40

POSITIVE LOGITS

InjectAttribute

0.52

ⓧ

0.50

NSIndexPath

0.49

ngdoc

0.47

 ProtoMessage

0.45

requestCode

0.44

ViewImports

0.44

 ModelExpression

0.42

gridx

0.42

addPreferredGap

0.42

Activations Density 0.625%

programming structures and syntax elements, particularly those related to loops and conditionals

Code that includes loop indices

loop counters and code structure

No Comments

No Known Activations