{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:25WXSAZFDS25U4WK2SCVGV22GZ","short_pith_number":"pith:25WXSAZF","canonical_record":{"source":{"id":"2411.01220","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-02T11:42:23Z","cross_cats_sorted":[],"title_canon_sha256":"f9e033a8ea19fc31b76deb2b965527566e7ec4e2538043476daace89a9be1585","abstract_canon_sha256":"502b31a76d456c739553d3a154e5943db9153b1c27b9e35c58fef4bd8a49f770"},"schema_version":"1.0"},"canonical_sha256":"d76d7903251cb5da72cad48553575a364fc8b8e96bff399eea6d9295f4a6a60a","source":{"kind":"arxiv","id":"2411.01220","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01220","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01220v2","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01220","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"25WXSAZFDS25","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"25WXSAZFDS25U4WK","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"25WXSAZF","created_at":"2026-07-05T09:31:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:25WXSAZFDS25U4WK2SCVGV22GZ","target":"record","payload":{"canonical_record":{"source":{"id":"2411.01220","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-02T11:42:23Z","cross_cats_sorted":[],"title_canon_sha256":"f9e033a8ea19fc31b76deb2b965527566e7ec4e2538043476daace89a9be1585","abstract_canon_sha256":"502b31a76d456c739553d3a154e5943db9153b1c27b9e35c58fef4bd8a49f770"},"schema_version":"1.0"},"canonical_sha256":"d76d7903251cb5da72cad48553575a364fc8b8e96bff399eea6d9295f4a6a60a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:50.819752Z","signature_b64":"rTwv/tR9Tuk7OEa/XK+4Q0q+39PrmIM49GVWPdWElSxkxFICzEcqKtIniH3CjRzWTAopTmdhyZx8ohLGX8FWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d76d7903251cb5da72cad48553575a364fc8b8e96bff399eea6d9295f4a6a60a","last_reissued_at":"2026-07-05T09:31:50.819246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:50.819246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.01220","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:31:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8PgaRV0tLaoDWQ5q4ROvROeo57q+ztHGGnC/2MTTTMs7lXBQ93p+RIP5WkpdkfosHlHHfQWr3GZKk+p9QzjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:09:57.164769Z"},"content_sha256":"e7830d2a1fb9e69358bae4e7690bd5dc8a236a5dbf8e396642934db4a7fc1d98","schema_version":"1.0","event_id":"sha256:e7830d2a1fb9e69358bae4e7690bd5dc8a236a5dbf8e396642934db4a7fc1d98"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:25WXSAZFDS25U4WK2SCVGV22GZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alasdair Paren, David Krueger, Fazl Barez, Luke Marks","submitted_at":"2024-11-02T11:42:23Z","abstract_excerpt":"Sparse Autoencoders (SAEs) have shown promise in improving the interpretability of neural network activations, but can learn features that are not features of the input, limiting their effectiveness. We propose \\textsc{Mutual Feature Regularization} \\textbf{(MFR)}, a regularization technique for improving feature learning by encouraging SAEs trained in parallel to learn similar features. We motivate \\textsc{MFR} by showing that features learned by multiple SAEs are more likely to correlate with features of the input. By training on synthetic data with known features of the input, we show that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01220","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.01220/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:31:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZXZNTyTJZjVDQvEuovpiH1O6gA05AMbied+Z3CzjvIOPxg/vBGY12R4n6f4BA/dQ30BxTDiukWjrKS9C1lnKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:09:57.165642Z"},"content_sha256":"6f81bec7296c74a68df63dffb122d288482636e60af3fe68bc3572bf3dad3a8e","schema_version":"1.0","event_id":"sha256:6f81bec7296c74a68df63dffb122d288482636e60af3fe68bc3572bf3dad3a8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/25WXSAZFDS25U4WK2SCVGV22GZ/bundle.json","state_url":"https://pith.science/pith/25WXSAZFDS25U4WK2SCVGV22GZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/25WXSAZFDS25U4WK2SCVGV22GZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T13:09:57Z","links":{"resolver":"https://pith.science/pith/25WXSAZFDS25U4WK2SCVGV22GZ","bundle":"https://pith.science/pith/25WXSAZFDS25U4WK2SCVGV22GZ/bundle.json","state":"https://pith.science/pith/25WXSAZFDS25U4WK2SCVGV22GZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/25WXSAZFDS25U4WK2SCVGV22GZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:25WXSAZFDS25U4WK2SCVGV22GZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"502b31a76d456c739553d3a154e5943db9153b1c27b9e35c58fef4bd8a49f770","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-02T11:42:23Z","title_canon_sha256":"f9e033a8ea19fc31b76deb2b965527566e7ec4e2538043476daace89a9be1585"},"schema_version":"1.0","source":{"id":"2411.01220","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01220","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01220v2","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01220","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"25WXSAZFDS25","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"25WXSAZFDS25U4WK","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"25WXSAZF","created_at":"2026-07-05T09:31:50Z"}],"graph_snapshots":[{"event_id":"sha256:6f81bec7296c74a68df63dffb122d288482636e60af3fe68bc3572bf3dad3a8e","target":"graph","created_at":"2026-07-05T09:31:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.01220/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse Autoencoders (SAEs) have shown promise in improving the interpretability of neural network activations, but can learn features that are not features of the input, limiting their effectiveness. We propose \\textsc{Mutual Feature Regularization} \\textbf{(MFR)}, a regularization technique for improving feature learning by encouraging SAEs trained in parallel to learn similar features. We motivate \\textsc{MFR} by showing that features learned by multiple SAEs are more likely to correlate with features of the input. By training on synthetic data with known features of the input, we show that ","authors_text":"Alasdair Paren, David Krueger, Fazl Barez, Luke Marks","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-02T11:42:23Z","title":"Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01220","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e7830d2a1fb9e69358bae4e7690bd5dc8a236a5dbf8e396642934db4a7fc1d98","target":"record","created_at":"2026-07-05T09:31:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"502b31a76d456c739553d3a154e5943db9153b1c27b9e35c58fef4bd8a49f770","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-02T11:42:23Z","title_canon_sha256":"f9e033a8ea19fc31b76deb2b965527566e7ec4e2538043476daace89a9be1585"},"schema_version":"1.0","source":{"id":"2411.01220","kind":"arxiv","version":2}},"canonical_sha256":"d76d7903251cb5da72cad48553575a364fc8b8e96bff399eea6d9295f4a6a60a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d76d7903251cb5da72cad48553575a364fc8b8e96bff399eea6d9295f4a6a60a","first_computed_at":"2026-07-05T09:31:50.819246Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:50.819246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rTwv/tR9Tuk7OEa/XK+4Q0q+39PrmIM49GVWPdWElSxkxFICzEcqKtIniH3CjRzWTAopTmdhyZx8ohLGX8FWAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:50.819752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01220","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7830d2a1fb9e69358bae4e7690bd5dc8a236a5dbf8e396642934db4a7fc1d98","sha256:6f81bec7296c74a68df63dffb122d288482636e60af3fe68bc3572bf3dad3a8e"],"state_sha256":"446c3c48e749fab7082d3f3a233feba2271481644d5239fba724dd677a12cecf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oqnHQY+6HBUhslSz9b7rFyhG38Yd0QMR15GHdDFKh92CS/datUO5mNV2KOik6qsXt216Tji3CiJ8KpVpCQQmDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:09:57.169916Z","bundle_sha256":"1bb83553858c6b14759172dc1622bd0ab6bbb1bad81e4e4532a2f0fc37ccaf0c"}}