[!TIP] This model is reproducible!See the README in thereproducedirectory for more information.
| Parameter | Value |
|---|---|
| direction_index | per layer |
| attn.o_proj.max_weight | 1.28 |
| attn.o_proj.max_weight_position | 29.79 |
| attn.o_proj.min_weight | 0.97 |
| attn.o_proj.min_weight_distance | 18.89 |
| mlp.down_proj.max_weight | 1.04 |
| mlp.down_proj.max_weight_position | 26.00 |
| mlp.down_proj.min_weight | 0.63 |
| mlp.down_proj.min_weight_distance | 21.07 |
| Metric | This model | Original model (adoringmc/squid-merged) |
|---|---|---|
| KL divergence | 0.2777 | 0 (by definition) |
| Refusals | 4/100 | 10/100 |
