Built site for gh-pages

.nojekyll

@@ -1 +1 @@
-7a8d4739
+dafc4add

index.html

@@ -143,7 +143,7 @@
 
 <div class="quarto-listing quarto-listing-container-grid" id="listing-listing">
 <div class="list grid quarto-listing-cols-3">
-<div class="g-col-1" data-index="0" data-listing-date-sort="1704326400000" data-listing-file-modified-sort="1705146805089" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="25">
+<div class="g-col-1" data-index="0" data-listing-date-sort="1705104000000" data-listing-file-modified-sort="1705146893489" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="25">
 <a href="./posts/TDC2023.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <p class="card-img-top"><img src="posts/TDC2023-sample-instances.png" style="height: 150px;"  class="thumbnail-image card-img"/></p>
@@ -159,14 +159,14 @@ <h5 class="no-anchor card-title listing-title">
 Zygimantas Straznickas, T. Ben Thompson, Michael Sklar
 </div>
 <div class="listing-date">
-Jan 4, 2024
+Jan 13, 2024
 </div>
 </div>
 </div>
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="1" data-listing-date-sort="1701302400000" data-listing-file-modified-sort="1705146805109" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7">
+<div class="g-col-1" data-index="1" data-listing-date-sort="1701302400000" data-listing-file-modified-sort="1705146893509" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7">
 <a href="./posts/fight_the_illusion.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <div class="listing-item-img-placeholder card-img-top" style="height: 150px;">&nbsp;</div>
@@ -189,7 +189,7 @@ <h5 class="no-anchor card-title listing-title">
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="2" data-listing-date-sort="1687651200000" data-listing-file-modified-sort="1705146805109" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7">
+<div class="g-col-1" data-index="2" data-listing-date-sort="1687651200000" data-listing-file-modified-sort="1705146893509" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7">
 <a href="./posts/catalog.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <p class="card-img-top"><img src="posts/catalog_files/figure-html/cell-9-output-1.png" style="height: 150px;"  class="thumbnail-image card-img"/></p>

posts/TDC2023.html

@@ -8,7 +8,7 @@
 
 <meta name="author" content="Zygimantas Straznickas">
 <meta name="author" content="Michael Sklar">
-<meta name="dcterms.date" content="2024-01-04">
+<meta name="dcterms.date" content="2024-01-13">
 <meta name="description" content="Summarizing our takeaways from TDC2023">
 
 <title>Confirm - Takeaways from the NeurIPS 2023 Trojan Detection Competition</title>
@@ -74,10 +74,10 @@
 <meta name="citation_title" content="Takeaways from the NeurIPS 2023 Trojan Detection Competition">
 <meta name="citation_author" content="Zygimantas Straznickas">
 <meta name="citation_author" content="Michael Sklar">
-<meta name="citation_publication_date" content="2024-01-04">
-<meta name="citation_cover_date" content="2024-01-04">
+<meta name="citation_publication_date" content="2024-01-13">
+<meta name="citation_cover_date" content="2024-01-13">
 <meta name="citation_year" content="2024">
-<meta name="citation_online_date" content="2024-01-04">
+<meta name="citation_online_date" content="2024-01-13">
 <meta name="citation_fulltext_html_url" content="https://confirmlabs.org/posts/TDC2023.html">
 <meta name="citation_language" content="en">
 </head>
@@ -157,7 +157,7 @@ <h1 class="title">Takeaways from the NeurIPS 2023 Trojan Detection Competition</
     <div>
     <div class="quarto-title-meta-heading">Published</div>
     <div class="quarto-title-meta-contents">
-      <p class="date">January 4, 2024</p>
+      <p class="date">January 13, 2024</p>
     </div>
   </div>
 
@@ -402,7 +402,7 @@ <h4 class="anchored" data-anchor-id="although-we-struggled-to-use-activation-eng
 <p>to compare/rank different sequences of tokens. Since <span class="math inline">\(u_i\)</span> is now a scalar for each x, given a collection of such x’s we can construct a z-score for our dataset as <span class="math inline">\((u_i - mean(u_i))/std(u_i)\)</span>, and rank them.</p>
 <div class="quarto-figure quarto-figure-left">
 <figure class="figure">
-<p><a href="TDC2023-sample-instances.png" class="lightbox" data-gallery="quarto-lightbox-gallery-1" title="The Z-scores of activation vector similarity for the provided sample instances"><img src="TDC2023-sample-instances.png" class="img-fluid figure-img" style="width:60.0%"></a></p>
+<p><a href="TDC2023-sample-instances.png" class="lightbox" title="The Z-scores of activation vector similarity for the provided sample instances" data-gallery="quarto-lightbox-gallery-1"><img src="TDC2023-sample-instances.png" class="img-fluid figure-img" style="width:60.0%"></a></p>
 <figcaption class="figure-caption">The Z-scores of activation vector similarity for the provided sample instances</figcaption>
 </figure>
 </div>
@@ -479,14 +479,14 @@ <h4 class="anchored" data-anchor-id="tricks-that-we-found-to-improve-performance
     Michael},
   title = {Takeaways from the {NeurIPS} 2023 {Trojan} {Detection}
     {Competition}},
-  date = {2024-01-04},
+  date = {2024-01-13},
   url = {https://confirmlabs.org/posts/TDC2023.html},
   langid = {en}
 }
 </code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre><div class="quarto-appendix-secondary-label">For attribution, please cite this work as:</div><div id="ref-straznickas2024" class="csl-entry quarto-appendix-citeas" role="listitem">
 <div class="">Z.
 Straznickas, T. B. Thompson, and M. Sklar, <span>“Takeaways from the
-NeurIPS 2023 Trojan Detection Competition,”</span> Jan. 04, 2024. <a href="https://confirmlabs.org/posts/TDC2023.html">https://confirmlabs.org/posts/TDC2023.html</a></div>
+NeurIPS 2023 Trojan Detection Competition,”</span> Jan. 13, 2024. <a href="https://confirmlabs.org/posts/TDC2023.html">https://confirmlabs.org/posts/TDC2023.html</a></div>
 </div></div></section></div></main> <!-- /main -->
 <script id="quarto-html-after-body" type="application/javascript">
 window.document.addEventListener("DOMContentLoaded", function (event) {
@@ -722,7 +722,7 @@ <h4 class="anchored" data-anchor-id="tricks-that-we-found-to-improve-performance
 });
 </script>
 </div> <!-- /content -->
-<script>var lightboxQuarto = GLightbox({"selector":".lightbox","openEffect":"zoom","closeEffect":"zoom","descPosition":"bottom","loop":true});</script>
+<script>var lightboxQuarto = GLightbox({"closeEffect":"zoom","loop":true,"selector":".lightbox","openEffect":"zoom","descPosition":"bottom"});</script>
 
 
 

posts/catalog.html

@@ -814,7 +814,7 @@ <h2 class="anchored" data-anchor-id="github">GitHub</h2>
 });
 </script>
 </div> <!-- /content -->
-<script>var lightboxQuarto = GLightbox({"descPosition":"bottom","openEffect":"zoom","selector":".lightbox","closeEffect":"zoom","loop":true});</script>
+<script>var lightboxQuarto = GLightbox({"closeEffect":"zoom","selector":".lightbox","openEffect":"zoom","descPosition":"bottom","loop":true});</script>
 
 
 

posts/catalog.out.ipynb

@@ -297,7 +297,7 @@
         "Pythia-12B is miscalibrated on 20% of the bigrams and 45% of the\n",
         "trigrams when we ask for prediction of $p \\geq 0.45$."
       ],
-      "id": "393b0a4d-96e5-4817-8f6d-8aa9874713ca"
+      "id": "1ec3c3b4-b659-498e-bc68-f2a8bbe54777"
     },
     {
       "cell_type": "code",
@@ -313,7 +313,7 @@
         }
       ],
       "source": [],
-      "id": "d6345904-eaa8-46a9-8a84-6af0a96ede58"
+      "id": "0e4f5b15-f23e-45cc-abf7-944935ed0841"
     },
     {
       "cell_type": "markdown",
@@ -377,7 +377,7 @@
         "The dataset is available on Huggingface:\n",
         "[pile_scan_4](https://huggingface.co/datasets/Confirm-Labs/pile_scan_4)"
       ],
-      "id": "9ac7dedc-2219-4841-994f-f0e278648347"
+      "id": "5ed0ab19-3c14-441e-adf5-ee50406f84cf"
     },
     {
       "cell_type": "code",
@@ -391,7 +391,7 @@
         }
       ],
       "source": [],
-      "id": "e45be69e-cb7d-446c-8379-e30e166022b6"
+      "id": "38552396-a4f9-4da2-8ee5-71390ae67081"
     },
     {
       "cell_type": "markdown",
@@ -423,7 +423,7 @@
         "Computational Linguistics, May 2022, pp. 95–136. doi:\n",
         "[10.18653/v1/2022.bigscience-1.9](https://doi.org/10.18653/v1/2022.bigscience-1.9).</span>"
       ],
-      "id": "1b4be320-18ff-4108-a568-431d308a4148"
+      "id": "6fc1d3c5-b97f-4c22-ae18-e8eb76855546"
     }
   ],
   "nbformat": 4,

search.json

@@ -53,7 +53,7 @@
     "href": "index.html",
     "title": "Confirm",
     "section": "",
-    "text": "Takeaways from the NeurIPS 2023 Trojan Detection Competition\n\n\nSummarizing our takeaways from TDC2023\n\n\n\nZygimantas Straznickas, T. Ben Thompson, Michael Sklar\n\n\nJan 4, 2024\n\n\n\n\n\n\n\n\n\n\n\n\n6 Ways to Fight the Interpretability Illusion\n\n\nNotes on using optimization and causal models for interpretability.\n\n\n\nMichael Sklar\n\n\nNov 30, 2023\n\n\n\n\n\n\n\n\n\n\n\n\nA catalog of several million tasks Pythia can do.\n\n\n\n\n\n\nT. Ben Thompson, Michael Sklar\n\n\nJun 25, 2023\n\n\n\n\n\n\n\n\nNo matching items"
+    "text": "Takeaways from the NeurIPS 2023 Trojan Detection Competition\n\n\nSummarizing our takeaways from TDC2023\n\n\n\nZygimantas Straznickas, T. Ben Thompson, Michael Sklar\n\n\nJan 13, 2024\n\n\n\n\n\n\n\n\n\n\n\n\n6 Ways to Fight the Interpretability Illusion\n\n\nNotes on using optimization and causal models for interpretability.\n\n\n\nMichael Sklar\n\n\nNov 30, 2023\n\n\n\n\n\n\n\n\n\n\n\n\nA catalog of several million tasks Pythia can do.\n\n\n\n\n\n\nT. Ben Thompson, Michael Sklar\n\n\nJun 25, 2023\n\n\n\n\n\n\n\n\nNo matching items"
   },
   {
     "objectID": "posts/fight_the_illusion.html",

sitemap.xml

@@ -2,18 +2,18 @@
 <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
   <url>
     <loc>https://confirmlabs.org/posts/catalog.html</loc>
-    <lastmod>2024-01-13T11:53:39.873Z</lastmod>
+    <lastmod>2024-01-13T11:55:08.657Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/posts/TDC2023.html</loc>
-    <lastmod>2024-01-13T11:53:36.773Z</lastmod>
+    <lastmod>2024-01-13T11:55:05.549Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/index.html</loc>
-    <lastmod>2024-01-13T11:53:35.349Z</lastmod>
+    <lastmod>2024-01-13T11:55:04.121Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/posts/fight_the_illusion.html</loc>
-    <lastmod>2024-01-13T11:53:37.433Z</lastmod>
+    <lastmod>2024-01-13T11:55:06.221Z</lastmod>
   </url>
 </urlset>