{"version":"1.0","provider_name":"MultAI","provider_url":"https:\/\/multai.eu\/en_gb","author_name":"hans","author_url":"https:\/\/multai.eu\/en_gb\/author\/hans\/","title":"Interpretable Features - MultAI","type":"rich","width":600,"height":338,"html":"<blockquote class=\"wp-embedded-content\" data-secret=\"EpRUg6JlwW\"><a href=\"https:\/\/multai.eu\/en_gb\/interpretable-features\/\">Interpretable Features<\/a><\/blockquote><iframe sandbox=\"allow-scripts\" security=\"restricted\" src=\"https:\/\/multai.eu\/en_gb\/interpretable-features\/embed\/#?secret=EpRUg6JlwW\" width=\"600\" height=\"338\" title=\"&#8220;Interpretable Features&#8221; &#8212; MultAI\" data-secret=\"EpRUg6JlwW\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" class=\"wp-embedded-content\"><\/iframe><script>\n\/*! This file is auto-generated *\/\n!function(d,l){\"use strict\";l.querySelector&&d.addEventListener&&\"undefined\"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!\/[^a-zA-Z0-9]\/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret=\"'+t.secret+'\"]'),o=l.querySelectorAll('blockquote[data-secret=\"'+t.secret+'\"]'),c=new RegExp(\"^https?:$\",\"i\"),i=0;i<o.length;i++)o[i].style.display=\"none\";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute(\"style\"),\"height\"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):\"link\"===t.message&&(r=new URL(s.getAttribute(\"src\")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener(\"message\",d.wp.receiveEmbedMessage,!1),l.addEventListener(\"DOMContentLoaded\",function(){for(var e,t,s=l.querySelectorAll(\"iframe.wp-embedded-content\"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute(\"data-secret\"))||(t=Math.random().toString(36).substring(2,12),e.src+=\"#?secret=\"+t,e.setAttribute(\"data-secret\",t)),e.contentWindow.postMessage({message:\"ready\",secret:t},\"*\")},!1)))}(window,document);\n\/\/# sourceURL=https:\/\/multai.eu\/wp-includes\/js\/wp-embed.min.js\n<\/script>\n","description":"Anthropic team uses sparse autoencoders to detect features in their Claude model. These features turn out to be highly abstract, multimodal and multilingual. Steering this features permits changing the model's behavior.","thumbnail_url":"https:\/\/wsw-int.de\/wp-content\/uploads\/2024\/05\/conflict-1024x973.png"}