representation
3 stories and discussions about representation, aggregated from every source we track.
1.
<p>This can be replicated with the code in the notebook: <a href="https://colab.research.google.com/github/likenneth/othello_world/blob/master/Othello_GPT_Circuits.ipynb" rel="ugc">https://colab.research.google.com/github/likenneth/othello_world/blob/master/Othello_GPT_Circuits.ipynb</a></p>
3.
Vision Language Models (VLMs) offer the exciting possibility of processing text as rendered images, bypassing the need for tokenizing the text into long token sequences. Since VLM image encoders map fixed-size images…