Transformer models that predict answers to addition questions
Philip Quirke
PhilipQuirke
AI & ML interests
AI Safety, Mechanistic Interpretability, Conservation
Recent Activity
authored
a paper
2 days ago
Understanding Addition in Transformers
authored
a paper
2 days ago
TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic
Interpretability Research
Organizations
models
56
PhilipQuirke/QuantaMaths_sub_d12_l2_h3_t75K_s371793
Updated
PhilipQuirke/QuantaMaths_sub_d8_l2_h3_t50K_s173289
Updated
PhilipQuirke/QuantaMaths_sub_d8_l2_h3_t50K_s371793
Updated
PhilipQuirke/QuantaMaths_sub_d6_l2_h3_t30K_s572091
Updated
PhilipQuirke/QuantaMaths_sub_d5_l2_h3_t30K_s372001
Updated
PhilipQuirke/QuantaMaths_mix_d9_l3_h4_t60K_s173289
Updated
PhilipQuirke/QuantaMaths_add_d6_l2_h3_t15K_s372001
Updated
PhilipQuirke/QuantaMaths_add_d5_l2_h3_t15K_s372001
Updated
PhilipQuirke/QuantaMaths_add_d6_l2_h3_t20K_s572091
Updated
PhilipQuirke/QuantaMaths_ins1_mix_d6_l3_h4_t40K_s372001
Updated
datasets
0
None public yet