Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
Paper • 2609.29845 • Published • 89
Shreyash Rampurkar
shreyash2512
·
AI & ML interests
yes
Recent Activity
upvoted a paper about 2 months ago
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs upvoted a paper about 2 months ago
Training Object Permanence in World Models upvoted an article about 2 months ago
Accelerating vision-language models with LFM2.5-VL-DSparkOrganizations
None yet
upvoted 2
papers about 2 months ago
upvoted an article about 2 months ago
Article
Accelerating vision-language models with LFM2.5-VL-DSpark
LiquidAI
• • 51