# Circuit Localization on Mixing dataset All tasks 1.0 (test) Source: [Circuit Localization on Mixing dataset All tasks 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-05-12T11:18:36.134Z Evaluation of model performance on the Circuit Localization task using the Mixing dataset All tasks 1.0 (test) split, reporting metrics such as CPR. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Circuit Localization | | Dataset (including any stated split) | Mixing dataset All tasks 1.0 (test) | | Metric | CPR | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 28 of 28 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [CPR](): Higher is better; unit: SCALAR. ## Recorded results | Method | CPR | Result date | Report paper | | --- | --- | --- | --- | | DCD-divisive-SVD | 1.035 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-agglom.-SVD | 1.034 | Not recorded | 6a02b45cdbc836b87d8249e8 | | K-Random | 1.033 | Not recorded | 6a02b45cdbc836b87d8249e8 | | K-representative | 1.026 | Not recorded | 6a02b45cdbc836b87d8249e8 | | K-Random | 1.021 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-kmeans-SVD | 1.021 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-kmeans-PCA | 1.021 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-divisive-SVD | 1.019 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-agglom.-SVD | 1.014 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-kmeans-SVD | 1.012 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-kmeans-PCA | 1.008 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-divisive-SVD | 0.98 | Not recorded | 6a02b45cdbc836b87d8249e8 | | EAP-IG | 0.977 | Not recorded | 6a02b45cdbc836b87d8249e8 | | K-Random | 0.97 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-kmeans-SVD | 0.967 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-kmeans-PCA | 0.967 | Not recorded | 6a02b45cdbc836b87d8249e8 | | EAP | 0.956 | Not recorded | 6a02b45cdbc836b87d8249e8 | | K-representative | 0.952 | Not recorded | 6a02b45cdbc836b87d8249e8 | | DCD-agglom.-SVD | 0.938 | Not recorded | 6a02b45cdbc836b87d8249e8 | | EAP-IG | 0.934 | Not recorded | 6a02b45cdbc836b87d8249e8 | | K-representative | 0.911 | Not recorded | 6a02b45cdbc836b87d8249e8 | | EAP | 0.885 | Not recorded | 6a02b45cdbc836b87d8249e8 | | EAP-IG | 0.869 | Not recorded | 6a02b45cdbc836b87d8249e8 | | EAP | 0.85 | Not recorded | 6a02b45cdbc836b87d8249e8 | | E-Act | 0.692 | Not recorded | 6a02b45cdbc836b87d8249e8 | | Random | 0.287 | Not recorded | 6a02b45cdbc836b87d8249e8 | | Random | 0.252 | Not recorded | 6a02b45cdbc836b87d8249e8 | | Random | 0.247 | Not recorded | 6a02b45cdbc836b87d8249e8 | ### DCD-divisive-SVD CPR: 1.035. Result ID: 6a030c7d47f34ce924e6cb89. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### DCD-agglom.-SVD CPR: 1.034. Result ID: 6a030c7d47f34ce924e6cb86. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### K-Random CPR: 1.033. Result ID: 6a030c7d47f34ce924e6cb7f. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### K-representative CPR: 1.026. Result ID: 6a030c7d47f34ce924e6cb82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### K-Random CPR: 1.021. Result ID: 6a030c7d47f34ce924e6cb80. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### DCD-kmeans-SVD CPR: 1.021. Result ID: 6a030c7d47f34ce924e6cb8b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### DCD-kmeans-PCA CPR: 1.021. Result ID: 6a030c7d47f34ce924e6cb8e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### DCD-divisive-SVD CPR: 1.019. Result ID: 6a030c7d47f34ce924e6cb88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### DCD-agglom.-SVD CPR: 1.014. Result ID: 6a030c7d47f34ce924e6cb85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### DCD-kmeans-SVD CPR: 1.012. Result ID: 6a030c7d47f34ce924e6cb8c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### DCD-kmeans-PCA CPR: 1.008. Result ID: 6a030c7d47f34ce924e6cb8f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### DCD-divisive-SVD CPR: 0.98. Result ID: 6a030c7d47f34ce924e6cb87. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### EAP-IG CPR: 0.977. Result ID: 6a030c7d47f34ce924e6cb75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### K-Random CPR: 0.97. Result ID: 6a030c7d47f34ce924e6cb7e. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### DCD-kmeans-SVD CPR: 0.967. Result ID: 6a030c7d47f34ce924e6cb8a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### DCD-kmeans-PCA CPR: 0.967. Result ID: 6a030c7d47f34ce924e6cb8d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### EAP CPR: 0.956. Result ID: 6a030c7d47f34ce924e6cb78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### K-representative CPR: 0.952. Result ID: 6a030c7d47f34ce924e6cb83. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### DCD-agglom.-SVD CPR: 0.938. Result ID: 6a030c7d47f34ce924e6cb84. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### EAP-IG CPR: 0.934. Result ID: 6a030c7d47f34ce924e6cb76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### K-representative CPR: 0.911. Result ID: 6a030c7d47f34ce924e6cb81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### EAP CPR: 0.885. Result ID: 6a030c7d47f34ce924e6cb79. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. ### EAP-IG CPR: 0.869. Result ID: 6a030c7d47f34ce924e6cb74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### EAP CPR: 0.85. Result ID: 6a030c7d47f34ce924e6cb77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### E-Act CPR: 0.692. Result ID: 6a030c7d47f34ce924e6cb7a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### Random CPR: 0.287. Result ID: 6a030c7d47f34ce924e6cb7b. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT2"}. This record does not assert independent reproduction. ### Random CPR: 0.252. Result ID: 6a030c7d47f34ce924e6cb7c. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama"}. This record does not assert independent reproduction. ### Random CPR: 0.247. Result ID: 6a030c7d47f34ce924e6cb7d. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.