INDEX

Explanations

keywords and identifiers related to programming and software development contexts

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

transaction operations

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

ніципалі

-0.76

 autorytatywna

-0.69

CppCodeGen

-0.67

 AssemblyProduct

-0.65

 informée

-0.65

 viewDidLoad

-0.63

 propOrder

-0.63

SharedCtor

-0.62

VYMaps

-0.60

 nahilalakip

-0.60

POSITIVE LOGITS

beginTransaction

0.88

Transaction

0.80

 transaction

0.60

 Transaction

0.60

transaction

0.58

getTransaction

0.55

 transactions

0.50

TRANSACTION

0.49

 Transactions

0.48

BagConstraints

0.48

Activations Density 0.001%

keywords and identifiers related to programming and software development contexts

transaction operations

No Comments

No Known Activations