Hugging Face's logo

dynamical-inference
/
consdl

Safetensors
sparse-autoencoder
dictionary-learning
interpretability
Model card Files
xet
 Community
jjho-choi commited on
Commit
0d3f0e7
·
verified ·
1 Parent(s): f43d1c5

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed0/model.safetensors +3 -0
  2. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed0/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt +3 -0
  3. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed0/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt +3 -0
  4. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed0/stats.fineweb.split_train.seed_no/max_act_per_token.pt +3 -0
  5. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed0/stats.fineweb.split_train.seed_no/mean_act_per_token.pt +3 -0
  6. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed0/stats.fineweb.split_train.seed_no/sparsity_per_token.pt +3 -0
  7. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed1/model.safetensors +3 -0
  8. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed1/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt +3 -0
  9. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed1/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt +3 -0
  10. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed1/stats.fineweb.split_train.seed_no/max_act_per_token.pt +3 -0
  11. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed1/stats.fineweb.split_train.seed_no/mean_act_per_token.pt +3 -0
  12. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed1/stats.fineweb.split_train.seed_no/sparsity_per_token.pt +3 -0
  13. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed2/model.safetensors +3 -0
  14. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed2/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt +3 -0
  15. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed2/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt +3 -0
  16. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed2/stats.fineweb.split_train.seed_no/max_act_per_token.pt +3 -0
  17. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed2/stats.fineweb.split_train.seed_no/mean_act_per_token.pt +3 -0
  18. lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed2/stats.fineweb.split_train.seed_no/sparsity_per_token.pt +3 -0
  19. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed0/model.safetensors +3 -0
  20. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed0/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt +3 -0
  21. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed0/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt +3 -0
  22. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed0/stats.fineweb.split_train.seed_no/max_act_per_token.pt +3 -0
  23. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed0/stats.fineweb.split_train.seed_no/mean_act_per_token.pt +3 -0
  24. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed0/stats.fineweb.split_train.seed_no/sparsity_per_token.pt +3 -0
  25. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed1/model.safetensors +3 -0
  26. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed1/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt +3 -0
  27. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed1/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt +3 -0
  28. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed1/stats.fineweb.split_train.seed_no/max_act_per_token.pt +3 -0
  29. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed1/stats.fineweb.split_train.seed_no/mean_act_per_token.pt +3 -0
  30. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed1/stats.fineweb.split_train.seed_no/sparsity_per_token.pt +3 -0
  31. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed2/model.safetensors +3 -0
  32. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed2/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt +3 -0
  33. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed2/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt +3 -0
  34. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed2/stats.fineweb.split_train.seed_no/max_act_per_token.pt +3 -0
  35. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed2/stats.fineweb.split_train.seed_no/mean_act_per_token.pt +3 -0
  36. lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed2/stats.fineweb.split_train.seed_no/sparsity_per_token.pt +3 -0
  37. lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed0/model.safetensors +3 -0
  38. lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed0/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt +3 -0
  39. lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed0/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt +3 -0
  40. lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed0/stats.fineweb.split_train.seed_no/max_act_per_token.pt +3 -0
  41. lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed0/stats.fineweb.split_train.seed_no/mean_act_per_token.pt +3 -0
  42. lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed0/stats.fineweb.split_train.seed_no/sparsity_per_token.pt +3 -0
  43. lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed1/model.safetensors +3 -0
  44. lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed2/model.safetensors +3 -0
  45. lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed2/stats.fineweb.split_train.seed_no/max_act_per_token.pt +3 -0
  46. lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed2/stats.fineweb.split_train.seed_no/mean_act_per_token.pt +3 -0
  47. lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed2/stats.fineweb.split_train.seed_no/sparsity_per_token.pt +3 -0
  48. lm/gpt2-small_layer8/matryoshka/x4/l0_128/seed1/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt +3 -0
  49. lm/gpt2-small_layer8/matryoshka/x4/l0_128/seed1/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt +3 -0
  50. lm/gpt2-small_layer8/matryoshka/x4/l0_128/seed1/stats.fineweb.split_train.seed_no/max_act_per_token.pt +3 -0
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed0/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ceabd4e9166bc0b2dd913ebd4e79d777180e9324d3ef27e287d154ca651caec
3
+ size 75550084
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed0/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ab9938de05e05814ce5818c2a61f86dc538cc2d43f0cea58f4474f16a9f7b03
3
+ size 99648
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed0/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9fed041cb0de18ef9973045e8085c8eaa4583052f2d5e612b0ae14cd731d57d
3
+ size 50471
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed0/stats.fineweb.split_train.seed_no/max_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48e84a2328151f4d6c541ed7e3f1ac7b1c4dab6c264e9cca3a574d6c46716fe
3
+ size 50382
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed0/stats.fineweb.split_train.seed_no/mean_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d642d6f050caa2594ce856f6269da1f1de25dbd0785d22574233c5bfc1f3430
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed0/stats.fineweb.split_train.seed_no/sparsity_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b750848308846d871f64cda77fae8ccf6af8d7115c5fc4be92c552cc3d19f28
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed1/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c050406278b0705b22a962c88566ed77a0dece186290947e50c4e89e683d742b
3
+ size 75550084
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed1/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d0ac454fe3ac6a1f78847ccba445ce576ba23c6d20508a6fad59d2110c9ae1
3
+ size 99648
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed1/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9942e10c8d14d41dc30e6cb8194682ac1d8c19c5f304d4091905301952b468c
3
+ size 50471
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed1/stats.fineweb.split_train.seed_no/max_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23d6e3db12b1d472643ea7c1585da559a8bee70aec0d20e43b606738a5cfc423
3
+ size 50382
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed1/stats.fineweb.split_train.seed_no/mean_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd90aec01ce35ea78c1068320a48001fe34ee52482241e458cedc45ea200cee
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed1/stats.fineweb.split_train.seed_no/sparsity_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df95a271b4e093a12d5bc26c9f86c9dd8ee2d38219b9e5592854af9b42fe3eb
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbe9a1426d8e3aeb8f7a5935ae3bb7e9d13671289582b913917215c1da48b473
3
+ size 75550084
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed2/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa59bcf16692ef0cfb51e0e170297003338378a54e3c396fb01d0f2602de5daa
3
+ size 99648
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed2/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3817ab5ec0f53dc68ef3ce38feadbfb4b3533414fffe322f524c16b6b85d715
3
+ size 50471
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed2/stats.fineweb.split_train.seed_no/max_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7c7aee9cb80aa7448b3cce3d2813786c73c1686ca3150ee723506d420b47f7f
3
+ size 50382
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed2/stats.fineweb.split_train.seed_no/mean_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14e97cd14152a0af1e20c0a8976b82338da5c5364a00ca0a871a3a5001c90dc
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_128/seed2/stats.fineweb.split_train.seed_no/sparsity_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5623570764b82468d3d47a766d8124b32215926cc2a5035e46c15b414d7bfbf4
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed0/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8324540298fd24181130435951594006dee2a8cb779f45c2c305ee143a32578
3
+ size 75550084
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed0/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3b9ebd8f2018b5df6ac293baba566ba9b5c3ec7ffa7154d16d2dcfc7c9aec41
3
+ size 99648
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed0/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e69d76780c5ade8c79407ca67193d5ffb451d8524374ca1f21fd4c24d766b3c
3
+ size 50471
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed0/stats.fineweb.split_train.seed_no/max_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f9bffd5cb60cf64dc05b57b2e5bb25a481d9822be5305030ee0aa73eb739559
3
+ size 50382
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed0/stats.fineweb.split_train.seed_no/mean_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574724ea6d70fbd56d28016b3a204a6f73e53c384d203cd555d5d808bdd12a2d
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed0/stats.fineweb.split_train.seed_no/sparsity_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c17df98965a2a2e0e2e7859639c976a6736426e340d59d7ce0058695bb79095d
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed1/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56415009ef9b7a52f22b0cb8a2d5b825699c3d9ed74343110b822d1f0c12e8e4
3
+ size 75550084
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed1/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d599a552c999b1acbe01e7303306c931a8fdea1238666ac8404c0cd42c256843
3
+ size 99648
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed1/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05de7912f6e05dfcd4cb5cb561e5ac7d2c432e093e3105472dbfd5b12362f235
3
+ size 50471
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed1/stats.fineweb.split_train.seed_no/max_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e8e533812d0b8c0695d8e65d059072349d4582bb032f8672f8da82d858139b
3
+ size 50382
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed1/stats.fineweb.split_train.seed_no/mean_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031a6e3b3d8c3e64c52ae13849ea5359a79c28e919f833ba6d91c4e95b9d5c2a
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed1/stats.fineweb.split_train.seed_no/sparsity_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da843c4721be949b2ac381725f6460af9db2a17fa5e2d5cad1d3f5685d5c18d7
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f167e8af3a3a644535f90908125c7e9893af8e4ab3c18a4ed3cf33c331dbff94
3
+ size 75550084
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed2/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eff1e319e3713a3421d8228d0bd52e28e1c2c8d1b19ed5d5e87273bc7a8b1994
3
+ size 99648
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed2/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a49b0ddd2b8284aab3a65c1217735d49cdb81f18cb6b80e43b19c93626e1272a
3
+ size 50471
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed2/stats.fineweb.split_train.seed_no/max_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24884f36d119db57d0b597ef71f57f2ac0bfe621492b28a2f90c3abcce5000b8
3
+ size 50382
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed2/stats.fineweb.split_train.seed_no/mean_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09797a01e5f6533c8d68b3a0a0284a0529de8bda7f3232450eefcd88b1454022
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_32/seed2/stats.fineweb.split_train.seed_no/sparsity_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:334fe20f43fd7b78ce95f3b880e77a8a8aed1a54eb23ec8155d2ebb2d3a3eda1
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed0/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddcf1f96782837b964695547c7c7620b9506616e86b59bc84601ad15b3c6631
3
+ size 75550084
lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed0/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdcb18cec5ebf95af2440e0f0e46ea5cc15b35a2d2b35a58ef8086cc1a9862dc
3
+ size 99648
lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed0/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:befe07c1cf702faf0e67d40faf577ad10f420eb8e02ad4088a2e302655ba5e73
3
+ size 50471
lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed0/stats.fineweb.split_train.seed_no/max_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4c2a5193f32363c7d620f4b828c7611e22ca1b5a1540d86e094665264663c61
3
+ size 50382
lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed0/stats.fineweb.split_train.seed_no/mean_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:738b600acdc41c9f3a9166ac9eb3a848feb066d8cc6d0a42f1f275e38a80e82d
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed0/stats.fineweb.split_train.seed_no/sparsity_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efca8a47e49729050665fa248852cc2fefdf34e416a67fbafac468da2b54c07f
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed1/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6474c1fb2c23045220ef280d93604fc48dff762a870d44fa158e267cf5bc5f96
3
+ size 75550084
lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578fca24ecb213a2df5ad60c578303a33109479f4c5b2876e6549948ff332abc
3
+ size 75550084
lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed2/stats.fineweb.split_train.seed_no/max_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1f6737670177ae7509b9a734dd67124de4baae0c08dce71284aca039d9ce07
3
+ size 50382
lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed2/stats.fineweb.split_train.seed_no/mean_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b337e211fe29bb83af60ac03a105eefbaddb921608ebc6bb327ff3d80e42ca
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x16/l0_64/seed2/stats.fineweb.split_train.seed_no/sparsity_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81d839f4faedd822174f7ae0a3ffcfe0867bc49c7a8897f0a6c8f4e38d6d43f3
3
+ size 50387
lm/gpt2-small_layer8/matryoshka/x4/l0_128/seed1/stats.fineweb.split_train.seed_no/active_count_hist_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1108c40e8e010258e043456fe70c07ffa5f4051eed147e4464754ac45257a919
3
+ size 25920
lm/gpt2-small_layer8/matryoshka/x4/l0_128/seed1/stats.fineweb.split_train.seed_no/firing_rate_per_latent.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43fd22c272a743d9da6898c4b5775c22fcb1197d90095e9c6345c4c8f2bdef98
3
+ size 13607
lm/gpt2-small_layer8/matryoshka/x4/l0_128/seed1/stats.fineweb.split_train.seed_no/max_act_per_token.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc943f223f066bbe1d230660db50434ee19f9e0c1fd24bc62cb2fca1af6e721b
3
+ size 13518