analiza aiqbench
This article details the application of Sparse Concept Anchoring (SCA) to transformer models, demonstrating how researchers can precisely locate and manipulate specific conceptual representations within the residual stream without compromising task performance. The work advances mechanistic interpretability by showing that abstract concepts, such as color mixing rules, can be reliably anchored in internal model states for potential steering applications.
Anchoring one concept in a transformer

We anchored a single concept (red) in the residual stream of a transformer. It ended up where we wanted, with nearby colors graded sensibly, and without degrading task accuracy. Steering is next. Earlier posts in this sequence introduced Sparse Concept Anchoring (SCA), tested in autoencoders. This post applies the technique to transformers. You don't need to have read the earlier posts to understand this one. Light revisions by Claude Fable 5, and experiments run with help from all the Claude 5s. Information flows through a transformer from input to output via the residual stream — an internal state, kind of like a mental state. It's composed of pieces, addressable by slice (layer) and position (token). At the input, each state is a token embedding. At deeper layers, the hidden states take on abstract meaning, being progressively transformed until they reach the final layer, where they are used to predict the next token. Those hidden states are the subject of a lot of mech interp research, because we (researchers) expect to find structure that reveals something about how the model "thinks" about the world[1]. In our experiments, we used a mini color-mixing language of expressions like "red + blue = purple". The models were trained to predict the answer, and they could do so accurately, even for pairs of colors they had never seen before. What would you expect to see, if you looked at the embeddings for the color tokens? We fit a linear probe on all the colors except the one being plotted, and decoded the held-out color with the probe. That was repeated for all colors in the vocabulary. Here's what we found: All 216 colors of our 6-subdivision RGB cube, decoded from embeddings with linear probes. Open rings mjx-container[jax="CHTML"] { line-height: 0; } mjx-container [space="1"] { margin-left: .111em; } mjx-container [space="2"] { margin-left: .167em; } mjx-container [space="3"] { margin-left: .222em; } mjx-container [space="4"] { margin-left: .278em; } mjx-container [space="5"] { margin-left: .333em; } mjx-container [rspace="1"] { margin-right: .111em; } mjx-container [rspace="2"] { margin-right: .167em; } mjx-container [rspace="3"] { margin-right: .222em; } mjx-container [rspace="4"] { margin-right: .278em; } mjx-container [rspace="5"] { margin-right: .333em; } mjx-container [size="s"] { font-size: 70.7%; } mjx-container [size="ss"] { font-size: 50%; } mjx-container [size="Tn"] { font-size: 60%; } mjx-container [size="sm"] { font-size: 85%; } mjx-container [size="lg"] { font-size: 120%; } mjx-container [size="Lg"] { font-size: 144%; } mjx-container [size="LG"] { font-size: 173%; } mjx-container [size="hg"] { font-size: 207%; } mjx-container [size="HG"] { font-size: 249%; } mjx-container [width="full"] { width: 100%; } mjx-box { display: inline-block; } mjx-block { display: block; } mjx-itable { display: inline-table; } mjx-row { display: table-row; } mjx-row > * { display: table-cell; } mjx-mtext { display: inline-block; text-align: left; } mjx-mstyle { display: inline-block; } mjx-merror { display: inline-block; color: red; background-color: yellow; } mjx-mphantom { visibility: hidden; } _::-webkit-full-page-media, _:future, :root mjx-container { will-change: opacity; } mjx-math { display: inline-block; text-align: left; line-height: 0; text-indent: 0; font-style: normal; font-weight: normal; font-size: 100%; font-size-adjust: none; letter-spacing: normal; border-collapse: collapse; word-wrap: normal; word-spacing: normal; white-space: nowrap; direction: ltr; padding: 1px 0; } mjx-container[jax="CHTML"][display="true"] { display: block; text-align: center; margin: 1em 0; } mjx-container[jax="CHTML"][display="true"][width="full"] { display: flex; } mjx-container[jax="CHTML"][display="true"] mjx-math { padding: 0; } mjx-container[jax="CHTML"][justify="left"] { text-align: left; } mjx-container[jax="CHTML"][justify="right"] { text-align: right; } mjx-TeXAtom { display: inline-block; text-align: left; } mjx-mo { display: inline-block; text-align: left; } mjx-stretchy-h { display: inline-table; width: 100%; } mjx-stretchy-h > * { display: table-cell; width: 0; } mjx-stretchy-h > * > mjx-c { display: inline-block; transform: scalex(1.0000001); } mjx-stretchy-h > * > mjx-c::before { display: inline-block; width: initial; } mjx-stretchy-h > mjx-ext { /* IE */ overflow: hidden; /* others */ overflow: clip visible; width: 100%; } mjx-stretchy-h > mjx-ext > mjx-c::before { transform: scalex(500); } mjx-stretchy-h > mjx-ext > mjx-c { width: 0; } mjx-stretchy-h > mjx-beg > mjx-c { margin-right: -.1em; } mjx-stretchy-h > mjx-end > mjx-c { margin-left: -.1em; } mjx-stretchy-v { display: inline-block; } mjx-stretchy-v > * { display: block; } mjx-stretchy-v > mjx-beg { height: 0; } mjx-stretchy-v > mjx-end > mjx
Citește articolul complet pe LessWrongSubiecte conexe
Metonymic Circuits for Abstract Concept Grounding in Vision Transformers
arXiv · 7 oct. 2026

The Five Realities of Existence, by Isaac Megbolugbe
promptnewsonline.com · 6 sept. 2026
Relational Semantic Grounding for Test-Time Discovery
arXiv · 15 oct. 2026
Inception in DiffusionGemma - Jailbreaking a Diffusion Language Model by Pinning Tokens Anywhere on the Canvas
LessWrong · 23 iul. 2026