INDEX

Explanations

programming-related keywords and structure definitions

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

setup and definition code

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

SqlClient

-0.47

/*

-0.44

DialogInterface

-0.42

 smtplib

-0.39

FileWriter

-0.36

 ActivatedRoute

-0.34

 MatDialog

-0.34

 ActionListener

-0.34

california

-0.34

 DialogInterface

-0.34

POSITIVE LOGITS

:✨

0.75

 propOrder

0.68

InjectMocks

0.60

!(:

0.59

OGND

0.58

 nakalista

0.57

AddHtmlAttribute

0.56

GEBURTSDATUM

0.56

 nahilalakip

0.55

beforeEach

0.53

Activations Density 0.001%

programming-related keywords and structure definitions

setup and definition code

No Comments

No Known Activations