Training Data PII Preview

Find emails, phones, card numbers, SSNs and IBANs in training text with exact checks, plus an optional AI model for names.

Runs in your browser.

Last updatedHow we build & check our tools

Interactive Tool

This tool runs in your browser and is loading now.

Enter your values once it appears to see your results.

How Training Data PII Preview works

Add your text and press Analyze locally. The default check runs fixed patterns in this browser tab with nothing to download, so it works on any device, and nothing you enter is sent to a server.

The default check needs no download. It scans your text with fixed patterns for identifiers that have an exact format: email addresses, phone numbers, payment card numbers (verified with the Luhn checksum), US Social Security numbers, IBANs (verified with the mod-97 checksum), IP addresses, dates written next to words like born or DOB, and tokens or keys inside URLs.

Each match is listed with most of the value hidden, and the redacted preview replaces it with its type in brackets. Names and street addresses have no fixed format, so patterns cannot find them; the language model options look for those in the already-redacted text.

Worked example

The model's output for the built-in sample, recorded on a desktop browser. Your run may word things slightly differently.

Training row: Jane Smith, jane.smith@example.com, 415-555-0199, account 8842, complaint about refund delay and home address in signature.
Found by pattern
Email address: j***@example.com Phone number: ending 0199
Redacted preview
Training row: Jane Smith, [EMAIL], [PHONE], account 8842, complaint about refund delay and home address in signature.
Risk from these matches
Low
Not checked by patterns
Names, street addresses and other free-text identifiers

The model

The files are served from this site, versioned so a cached copy is never stale. Nothing is fetched from a third party while you use the tool.

You can switch models in the tool. Also available: Gemma 4 E2B instruction-tuned (web build) (2.0 GB). The larger language model gives more thorough answers but is a bigger download and needs a stronger device.

ModelDownloadRuns onLicence
Gemma 4 E2B instruction-tuned (web build)2.0 GBGraphics card (WebGPU)Apache-2.0

Limitations

  • Patterns miss identifiers written in unusual ways (a phone number spelled out in words, a card number split across lines) and do not see names, street addresses or account usernames.
  • A clean result is not proof the text is free of personal data. Review it before sharing or training on it.
  • Results describe the input you gave, not the real-world situation behind it. Review them yourself before acting.

Good uses

  • Triage AI operations notes before deeper review
  • Prepare consistent labels for repeat workflows
  • Reduce manual sorting on small batches
  • Keep sensitive drafts in the browser preview

Frequently Asked Questions

Common questions about the Training Data PII Preview

No. The model files download from this site once, and then everything runs in your browser tab. The text you enter is never sent to a server, and closing the tab discards it.
From the same team

Stop paying per token — route AI requests to your own GPU

Wide Area AI is a local-first AI gateway: repeated requests hit an edge cache, the rest run free on your own hardware, and the cloud is only a failover. OpenAI-compatible endpoint, free tier.

Start routing — free
VRAM CalculatorCan I Run This AI?AI API Cost CalculatorGPU for Model

Explore More Tools

Explore these related tools for your next step.

ai

LLM VRAM Calculator

Calculate how much VRAM any LLM needs to run locally — pick a model (Llama, Gemma, Qwen, DeepSeek, or search Hugging Face), choose a quantization and context size, and see which GPUs it fits on, including multi-GPU setups.

Try it now
ai

LLM Inference Speed Calculator

Estimate LLM tokens per second from memory bandwidth, model size, quantization, and context window. Compare generation speed across GPUs (RTX 4090, 5090, A100, H100, Apple Silicon) and understand the memory-bandwidth bottleneck.

Try it now
ai

What LLM Can I Run?

Detect your GPU with one click and see which LLMs your computer can actually run — Llama, Gemma, Qwen, DeepSeek and 50+ more, ranked by whether they fit in your VRAM, need CPU offloading, or won't run at all.

Try it now
ai

Fine-Tuning VRAM Calculator

Calculate VRAM requirements for fine-tuning LLMs with full fine-tuning, LoRA, or QLoRA. Accounts for gradients, optimizer states, activations, batch size, and gradient checkpointing — see which GPUs can train each model.

Try it now
ai

Ollama Command Builder

Build Ollama commands without memorizing syntax: run, pull, and create commands for any model, complete Modelfiles with parameters and system prompts, and server environment configuration — with built-in VRAM checks.

Try it now
ai

Self-Hosted LLM Cost Calculator

Is it cheaper to self-host an LLM or use an API? Compare GPT, Claude, and Gemini API costs against running open models on your own hardware or cloud GPUs — with break-even timelines and capacity checks.

Try it now