- I am an AI Researcher specializing in Mechanistic Interpretability and Knowledge Editing.
- Currently completing my M.Sc. in Computer Science, where I research methods to edit LLMs knowledge
- Previously, I spent 4+ years as a Software Engineer. I now leverage that engineering background to build scalable, clean, and reproducible research codebases, bridging the gap between theoretical research and production engineering.
🎯
Focusing
AI Researcher & Engineer | Mechanistic Interpretability & Knowledge Editing
-
西北工业大学
- Xi'an, China
-
15:43
(UTC +08:00) - https://orcid.org/0009-0004-6701-5466
- in/jasonrichdarmawan
- https://jasonrichdarmawan.odoo.com
- https://bit.ly/CVJasonRich
- https://bit.ly/WorkingWithJason
Highlights
- Pro
Pinned Loading
-
-
steering-model-with-latent-reasoning
steering-model-with-latent-reasoning PublicMinimal code to extract and apply steering vectors to a model with latent reasoning from the paper "Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach"
-
SAELens
SAELens PublicForked from decoderesearch/SAELens
Training Sparse Autoencoders on Language Models
Python
-
SONAR
SONAR PublicForked from facebookresearch/SONAR
SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.
Python
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.


