Built site for gh-pages

.nojekyll

@@ -1 +1 @@
-0de228ad
+e27ba027

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="1705968000000" data-listing-file-modified-sort="1706115221300" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="4">
+<div class="g-col-1" data-index="0" data-listing-date-sort="1705968000000" data-listing-file-modified-sort="1706120751249" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="4">
 <a href="./posts/dreamy.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <p class="card-img-top"><img src="posts/dream_wow.png" style="height: 150px;"  class="thumbnail-image card-img"/></p>
@@ -166,7 +166,7 @@ <h5 class="no-anchor card-title listing-title">
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="1" data-listing-date-sort="1705104000000" data-listing-file-modified-sort="1706115221272" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="25">
+<div class="g-col-1" data-index="1" data-listing-date-sort="1705104000000" data-listing-file-modified-sort="1706120751221" 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>
@@ -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="1701302400000" data-listing-file-modified-sort="1706115221300" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7">
+<div class="g-col-1" data-index="2" data-listing-date-sort="1701302400000" data-listing-file-modified-sort="1706120751249" 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>
@@ -212,7 +212,7 @@ <h5 class="no-anchor card-title listing-title">
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="3" data-listing-date-sort="1687651200000" data-listing-file-modified-sort="1706115221292" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7">
+<div class="g-col-1" data-index="3" data-listing-date-sort="1687651200000" data-listing-file-modified-sort="1706120751241" 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

@@ -352,7 +352,7 @@ <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" 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>
+<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>
 <figcaption class="figure-caption">The Z-scores of activation vector similarity for the provided sample instances</figcaption>
 </figure>
 </div>
@@ -722,7 +722,7 @@ <h4 class="anchored" data-anchor-id="trojan-recovery">Trojan recovery:</h4>
 });
 </script>
 </div> <!-- /content -->
-<script>var lightboxQuarto = GLightbox({"selector":".lightbox","closeEffect":"zoom","loop":true,"descPosition":"bottom","openEffect":"zoom"});</script>
+<script>var lightboxQuarto = GLightbox({"closeEffect":"zoom","selector":".lightbox","loop":true,"openEffect":"zoom","descPosition":"bottom"});</script>
 
 
 

posts/catalog.html

@@ -823,7 +823,7 @@ <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({"descPosition":"bottom","loop":true,"openEffect":"zoom","selector":".lightbox","closeEffect":"zoom"});</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": "06c9d831-1c49-4989-a26e-4a8e9af18173"
+      "id": "5dd96a6b-f902-491d-897a-761873a63d92"
     },
     {
       "cell_type": "code",
@@ -313,7 +313,7 @@
         }
       ],
       "source": [],
-      "id": "21157758-0f9e-4e85-b726-edfffbffd00b"
+      "id": "2a4e93cb-ea85-4eaa-840b-8fcc4afc2fee"
     },
     {
       "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": "8a452dff-613c-4c99-9047-d6a42dbf494a"
+      "id": "1ab74550-3521-4dfa-ab3c-032021e2f440"
     },
     {
       "cell_type": "code",
@@ -391,7 +391,7 @@
         }
       ],
       "source": [],
-      "id": "554bfd30-557d-45d0-81ff-1011fd3506b1"
+      "id": "330079d0-f60c-49e5-82e0-766e0ba7a91f"
     },
     {
       "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": "c8f430e1-ffd8-4dfe-8a28-b842a4f61b98"
+      "id": "875e30e7-98aa-49bd-a1c3-b23e310cc97d"
     }
   ],
   "nbformat": 4,

posts/dreamy.html

@@ -247,6 +247,7 @@ <h1 class="title">Fluent dreaming for language models</h1>
 </header>
 
 <p>This is a companion page for our paper, <a href="http:///arxiv">“Fluent dreaming for language models.” (arXiv link)</a>.</p>
+<p>There is an <a href="https://colab.research.google.com/drive/1B0dM7du91BUkT7tSICXjKL7lrBAEdSa-?usp=sharing">interactive demo of this page on Colab.</a></p>
 <div class="callout callout-style-simple callout-note no-icon callout-titled" title="Dreaming Phi-2">
 <div class="callout-header d-flex align-content-center">
 <div class="callout-icon-container">
@@ -5211,7 +5212,7 @@ <h2 class="anchored" data-anchor-id="causal-token-attribution">Causal token attr
 });
 </script>
 </div> <!-- /content -->
-<script>var lightboxQuarto = GLightbox({"descPosition":"bottom","openEffect":"zoom","loop":true,"selector":".lightbox","closeEffect":"zoom"});</script>
+<script>var lightboxQuarto = GLightbox({"descPosition":"bottom","selector":".lightbox","loop":true,"openEffect":"zoom","closeEffect":"zoom"});</script>
 
 
 

search.json

@@ -39,7 +39,7 @@
     "href": "posts/dreamy.html",
     "title": "Fluent dreaming for language models",
     "section": "",
-    "text": "This is a companion page for our paper, “Fluent dreaming for language models.” (arXiv link).\nDreaming is the process of maximizing some internal or output feature of a neural network by iteratively tweaking the input to the network. The most well-known example is DeepDream [1]. Besides making pretty images, dreaming is useful for interpreting the purpose of the internal components of a neural network [2]–[4]. To our knowledge, Dreaming has previously only been applied to vision models because the input space to a vision model is approximately continuous and algorithms like gradient descent work well. For language models, the input space is discrete and very different algorithms are needed. Extending work in the adversarial attacks literature [5], in the paper, we introduce the Evolutionary Prompt Optimization (EPO) algorithm for dreaming with language models.\nOn this page, we demonstrate running the EPO algorithm for a neuron in Phi-2. There is also a Colab notebook version of this page available."
+    "text": "This is a companion page for our paper, “Fluent dreaming for language models.” (arXiv link).\nThere is an interactive demo of this page on Colab.\nDreaming is the process of maximizing some internal or output feature of a neural network by iteratively tweaking the input to the network. The most well-known example is DeepDream [1]. Besides making pretty images, dreaming is useful for interpreting the purpose of the internal components of a neural network [2]–[4]. To our knowledge, Dreaming has previously only been applied to vision models because the input space to a vision model is approximately continuous and algorithms like gradient descent work well. For language models, the input space is discrete and very different algorithms are needed. Extending work in the adversarial attacks literature [5], in the paper, we introduce the Evolutionary Prompt Optimization (EPO) algorithm for dreaming with language models.\nOn this page, we demonstrate running the EPO algorithm for a neuron in Phi-2. There is also a Colab notebook version of this page available."
   },
   {
     "objectID": "posts/dreamy.html#installation-and-setup",

sitemap.xml

@@ -2,22 +2,22 @@
 <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
   <url>
     <loc>https://confirmlabs.org/posts/catalog.html</loc>
-    <lastmod>2024-01-24T16:53:58.704Z</lastmod>
+    <lastmod>2024-01-24T18:26:08.485Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/posts/dreamy.html</loc>
-    <lastmod>2024-01-24T16:53:55.428Z</lastmod>
+    <lastmod>2024-01-24T18:26:05.281Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/index.html</loc>
-    <lastmod>2024-01-24T16:53:52.504Z</lastmod>
+    <lastmod>2024-01-24T18:26:02.353Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/posts/TDC2023.html</loc>
-    <lastmod>2024-01-24T16:53:53.968Z</lastmod>
+    <lastmod>2024-01-24T18:26:03.825Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/posts/fight_the_illusion.html</loc>
-    <lastmod>2024-01-24T16:53:56.140Z</lastmod>
+    <lastmod>2024-01-24T18:26:05.997Z</lastmod>
   </url>
 </urlset>