INDEX

Explanations

technical terms and phrases related to programming concepts and code structure

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

Code, programming, or comments

np_acts-logits-general · gemini-2.0-flash

programming code debugging correctness

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

المناصب

-0.65

 فريبيس

-0.61

لينكات

-0.59

ArgumentParser

-0.57

évaluateur

-0.54

istoitu

-0.53

INCREF

-0.50

NgModule

-0.49

 gyhoeddwyd

-0.49

GEBURTS

-0.48

POSITIVE LOGITS

 programming

0.47

 Programming

0.45

 programmer

0.44

 Programmer

0.43

 program

0.38

Programming

0.38

Giz

0.37

 programmers

0.34

AutoScaleMode

0.33

 Program

0.33

Activations Density 1.272%

technical terms and phrases related to programming concepts and code structure

Code, programming, or comments

programming code debugging correctness

No Comments

No Known Activations