INDEX

Explanations

code snippets and configurations related to software development, specifically in programming contexts

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

Ruby programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

RegressionTest

-0.58

findpost

-0.55

 betweenstory

-0.54

 ویکی‌آمباردا

-0.48

 defaultstate

-0.47

DoubleQuotes

-0.45

InjectAttribute

-0.43

 محفوظة

-0.43

 lenker

-0.40

 للمعارف

-0.40

POSITIVE LOGITS

 suffit

0.44

 gezet

0.41

 zetten

0.41

 contaminated

0.40

antMatchers

0.39

 LEGAL

0.38

 Boston

0.38

endregion

0.38

isDebugEnabled

0.38

 rispondere

0.38

Activations Density 0.084%

code snippets and configurations related to software development, specifically in programming contexts

Ruby programming constructs

No Comments

No Known Activations