Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- attn_out_all/layer_0_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_0_width_262k_l0_small/config.json +9 -0
- attn_out_all/layer_11_width_262k_l0_small/config.json +9 -0
- attn_out_all/layer_13_width_16k_l0_big/config.json +9 -0
- attn_out_all/layer_14_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_14_width_262k_l0_big/config.json +9 -0
- attn_out_all/layer_15_width_16k_l0_big/config.json +9 -0
- attn_out_all/layer_15_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_17_width_262k_l0_big/config.json +9 -0
- attn_out_all/layer_17_width_262k_l0_small/config.json +9 -0
- attn_out_all/layer_18_width_262k_l0_big/config.json +9 -0
- attn_out_all/layer_18_width_262k_l0_small/config.json +9 -0
- attn_out_all/layer_19_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_20_width_262k_l0_small/config.json +9 -0
- attn_out_all/layer_21_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_22_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_24_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_24_width_262k_l0_big/config.json +9 -0
- attn_out_all/layer_25_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_25_width_262k_l0_big/config.json +9 -0
- attn_out_all/layer_25_width_262k_l0_small/config.json +9 -0
- attn_out_all/layer_26_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_26_width_262k_l0_big/config.json +9 -0
- attn_out_all/layer_27_width_16k_l0_big/config.json +9 -0
- attn_out_all/layer_27_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_28_width_16k_l0_big/config.json +9 -0
- attn_out_all/layer_28_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_29_width_16k_l0_big/config.json +9 -0
- attn_out_all/layer_29_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_2_width_16k_l0_big/config.json +9 -0
- attn_out_all/layer_30_width_16k_l0_big/config.json +9 -0
- attn_out_all/layer_31_width_262k_l0_small/config.json +9 -0
- attn_out_all/layer_32_width_262k_l0_big/config.json +9 -0
- attn_out_all/layer_33_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_34_width_262k_l0_small/config.json +9 -0
- attn_out_all/layer_35_width_262k_l0_big/config.json +9 -0
- attn_out_all/layer_36_width_262k_l0_big/config.json +9 -0
- attn_out_all/layer_37_width_16k_l0_big/config.json +9 -0
- attn_out_all/layer_37_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_38_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_38_width_262k_l0_big/config.json +9 -0
- attn_out_all/layer_39_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_3_width_262k_l0_big/config.json +9 -0
- attn_out_all/layer_41_width_16k_l0_big/config.json +9 -0
- attn_out_all/layer_41_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_41_width_262k_l0_big/config.json +9 -0
- attn_out_all/layer_43_width_16k_l0_big/config.json +9 -0
- attn_out_all/layer_43_width_16k_l0_small/config.json +9 -0
- attn_out_all/layer_44_width_16k_l0_big/config.json +9 -0
- attn_out_all/layer_45_width_16k_l0_big/config.json +9 -0
attn_out_all/layer_0_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.0.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.0.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 10,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_0_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.0.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.0.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 10,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_11_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.11.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.11.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 15,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_13_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.13.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.13.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 97,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_14_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.14.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.14.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 16,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_14_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.14.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.14.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 100,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_15_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.15.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.15.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 103,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_15_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.15.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.15.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 17,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_17_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.17.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.17.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 109,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_17_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.17.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.17.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 18,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_18_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.18.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.18.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 112,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_18_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.18.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.18.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 18,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_19_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.19.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.19.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 19,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_20_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.20.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.20.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 19,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_21_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.21.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.21.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_22_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.22.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.22.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_24_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.24.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.24.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_24_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.24.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.24.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_25_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.25.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.25.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_25_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.25.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.25.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_25_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.25.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.25.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_26_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.26.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.26.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_26_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.26.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.26.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_27_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.27.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.27.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_27_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.27.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.27.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_28_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.28.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.28.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_28_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.28.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.28.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_29_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.29.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.29.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_29_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.29.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.29.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_2_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.2.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.2.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 65,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_30_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.30.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.30.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_31_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.31.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.31.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_32_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.32.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.32.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_33_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.33.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.33.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_34_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.34.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.34.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_35_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.35.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.35.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_36_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.36.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.36.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_37_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.37.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.37.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_37_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.37.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.37.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_38_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.38.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.38.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_38_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.38.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.38.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_39_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.39.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.39.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_3_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.3.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.3.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 68,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_41_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.41.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.41.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_41_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.41.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.41.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_41_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.41.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.41.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_43_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.43.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.43.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_43_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.43.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.43.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_44_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.44.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.44.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|
attn_out_all/layer_45_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.45.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.45.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "gemma-v3-27b-it",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false
|
| 9 |
+
}
|