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/layer_16_width_16k_l0_big/config.json +10 -0
- attn_out/layer_16_width_16k_l0_small/config.json +10 -0
- attn_out/layer_16_width_262k_l0_medium/config.json +10 -0
- attn_out/layer_16_width_262k_l0_small/config.json +10 -0
- attn_out/layer_16_width_65k_l0_big/config.json +10 -0
- attn_out/layer_16_width_65k_l0_medium/config.json +10 -0
- attn_out/layer_16_width_65k_l0_small/config.json +10 -0
- attn_out/layer_31_width_16k_l0_big/config.json +10 -0
- attn_out/layer_31_width_262k_l0_big/config.json +10 -0
- attn_out/layer_31_width_262k_l0_medium/config.json +10 -0
- attn_out/layer_31_width_65k_l0_big/config.json +10 -0
- attn_out/layer_31_width_65k_l0_medium/config.json +10 -0
- attn_out/layer_31_width_65k_l0_small/config.json +10 -0
- attn_out/layer_40_width_16k_l0_big/config.json +10 -0
- attn_out/layer_40_width_262k_l0_big/config.json +10 -0
- attn_out/layer_40_width_262k_l0_small/config.json +10 -0
- attn_out/layer_40_width_65k_l0_medium/config.json +10 -0
- attn_out/layer_40_width_65k_l0_small/config.json +10 -0
- attn_out/layer_53_width_16k_l0_medium/config.json +10 -0
- attn_out/layer_53_width_16k_l0_small/config.json +10 -0
- attn_out/layer_53_width_262k_l0_big/config.json +10 -0
- attn_out/layer_53_width_65k_l0_medium/config.json +10 -0
- attn_out_all/layer_0_width_262k_l0_big/config.json +10 -0
- attn_out_all/layer_12_width_262k_l0_small/config.json +10 -0
- attn_out_all/layer_13_width_16k_l0_big/config.json +10 -0
- attn_out_all/layer_13_width_16k_l0_small/config.json +10 -0
- attn_out_all/layer_14_width_16k_l0_small/config.json +10 -0
- attn_out_all/layer_16_width_262k_l0_big/config.json +10 -0
- attn_out_all/layer_20_width_16k_l0_big/config.json +10 -0
- attn_out_all/layer_20_width_16k_l0_small/config.json +10 -0
- attn_out_all/layer_21_width_16k_l0_big/config.json +10 -0
- attn_out_all/layer_21_width_262k_l0_small/config.json +10 -0
- attn_out_all/layer_22_width_262k_l0_small/config.json +10 -0
- attn_out_all/layer_25_width_262k_l0_big/config.json +10 -0
- attn_out_all/layer_25_width_262k_l0_small/config.json +10 -0
- attn_out_all/layer_26_width_16k_l0_big/config.json +10 -0
- attn_out_all/layer_26_width_16k_l0_small/config.json +10 -0
- attn_out_all/layer_28_width_262k_l0_small/config.json +10 -0
- attn_out_all/layer_29_width_16k_l0_big/config.json +10 -0
- attn_out_all/layer_29_width_16k_l0_small/config.json +10 -0
- attn_out_all/layer_2_width_262k_l0_big/config.json +10 -0
- attn_out_all/layer_30_width_262k_l0_big/config.json +10 -0
- attn_out_all/layer_31_width_16k_l0_small/config.json +10 -0
- attn_out_all/layer_31_width_262k_l0_small/config.json +10 -0
- attn_out_all/layer_32_width_16k_l0_big/config.json +10 -0
- attn_out_all/layer_33_width_16k_l0_big/config.json +10 -0
- attn_out_all/layer_34_width_16k_l0_big/config.json +10 -0
- attn_out_all/layer_35_width_16k_l0_small/config.json +10 -0
- attn_out_all/layer_35_width_262k_l0_small/config.json +10 -0
- attn_out_all/layer_37_width_262k_l0_big/config.json +10 -0
attn_out/layer_16_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.16.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.16.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 129,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_16_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.16.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.16.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 17,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_16_width_262k_l0_medium/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.16.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.16.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 53,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_16_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.16.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.16.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 17,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_16_width_65k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.16.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.16.self_attn.o_proj.input",
|
| 4 |
+
"width": 65536,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 129,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_16_width_65k_l0_medium/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.16.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.16.self_attn.o_proj.input",
|
| 4 |
+
"width": 65536,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 53,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_16_width_65k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.16.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.16.self_attn.o_proj.input",
|
| 4 |
+
"width": 65536,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 17,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_31_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 16384,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 150,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_31_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 150,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_31_width_262k_l0_medium/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 60,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_31_width_65k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 65536,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 150,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_31_width_65k_l0_medium/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 65536,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 60,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_31_width_65k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 65536,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_40_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.40.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.40.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 150,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_40_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.40.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.40.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 150,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_40_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.40.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.40.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_40_width_65k_l0_medium/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.40.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.40.self_attn.o_proj.input",
|
| 4 |
+
"width": 65536,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 60,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_40_width_65k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.40.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.40.self_attn.o_proj.input",
|
| 4 |
+
"width": 65536,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_53_width_16k_l0_medium/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.53.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.53.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 60,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_53_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.53.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.53.self_attn.o_proj.input",
|
| 4 |
+
"width": 16384,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_53_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.53.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.53.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 150,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out/layer_53_width_65k_l0_medium/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.53.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.53.self_attn.o_proj.input",
|
| 4 |
+
"width": 65536,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 60,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_0_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 60,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_12_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.12.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.12.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 15,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_13_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 97,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_13_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 16,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_14_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 16,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_16_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hf_hook_point_in": "model.layers.16.self_attn.o_proj.input",
|
| 3 |
+
"hf_hook_point_out": "model.layers.16.self_attn.o_proj.input",
|
| 4 |
+
"width": 262144,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 106,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_20_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 16384,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 118,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_20_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 16384,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 19,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_21_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_21_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 262144,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_22_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 262144,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_25_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_25_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_26_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_26_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_28_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 262144,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_29_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_29_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_2_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 262144,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 65,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_30_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 262144,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_31_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 16384,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_31_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_32_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 16384,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_33_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_34_width_16k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 16384,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_35_width_16k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 16384,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_35_width_262k_l0_small/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 20,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|
attn_out_all/layer_37_width_262k_l0_big/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 262144,
|
| 5 |
+
"model_name": "google/gemma-3-27b-pt",
|
| 6 |
+
"architecture": "jump_relu",
|
| 7 |
+
"l0": 120,
|
| 8 |
+
"affine_connection": false,
|
| 9 |
+
"type": "sae"
|
| 10 |
+
}
|