INDEX

Explanations

syntactical structure and programming keywords commonly used in code, particularly in terms of function definitions and database operations

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

code and citations

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

 contextLoads

-0.55

msgSender

-0.50

protoimpl

-0.50

'{@

-0.48

CUSSION

-0.45

تقاوى

-0.45

 initComponents

-0.45

Personendaten

-0.44

AddTagHelper

-0.44

 assessments

-0.43

POSITIVE LOGITS

 ویکی‌آمباردا

0.44

 Sosten

0.41

Personensuche

0.40

 تضيفلها

0.39

 defaultstate

0.38

aimana

0.36

SqlSession

0.35

 Lingkungan

0.35

 grossen

0.35

 especializado

0.35

Activations Density 0.001%

syntactical structure and programming keywords commonly used in code, particularly in terms of function definitions and database operations

code and citations

No Comments

No Known Activations