Sign up to save your podcasts
Or
Share “In-context learning of representations can be explained by induction circuits” by Andy Arditi
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
“In-context learning of representations can be explained by induction circuits” by Andy Arditi
This is a crosspost of my ICLR 2026 blogpost track post. All code and experiments are available at github.com/andyrdt/iclr_induction.
Summary
Park et al., 2025 show that when large language models (LLMs) process random walks on a graph, their internal representations come to mirror the underlying graph's structure. The authors interpret this broadly, suggesting that LLMs can "manipulate their representations in order to reflect concept semantics specified entirely in-context". In this post, we take a closer look at the underlying mechanism, and suggest a simpler explanation. We argue that induction circuits (Elhage et al., 2021; Olsson et al., 2022), a well-known mechanism for in-context bigram recall, suffice to explain both the task performance and the representation geometry observed by Park et al.
Recapitulation and reproduction of Park et al., 2025
We begin by describing the experimental setup of Park et al., 2025 and reproducing their main results on Llama-3.1-8B.
Figure 1. Overview of Park et al.(a) The grid tracing task uses a 4×4 grid of words. (b) Models observe random walks on the grid (e.g., apple bird milk sand sun plane opera ...) where consecutive words are always neighbors. As the sequence length grows, the model begins to predict valid [...]
---
Outline:
(00:20) Summary
(01:06) Recapitulation and reproduction of Park et al., 2025
(02:03) The grid tracing task
(04:36) Reproduction and Park et al.s interpretation
(06:19) A simpler explanation: induction circuits
(07:32) Testing the induction hypothesis
(08:45) Results
(11:25) Previous-token mixing can account for representation geometry
(11:52) The neighbor-mixing hypothesis
(12:50) A toy model of previous-token mixing
(13:56) Evidence of neighbor mixing in individual model activations
(15:34) Limitations
(17:57) Conclusion
The original text contained 4 footnotes which were omitted from this narration.
---
First published:
March 2nd, 2026
Source:
https://www.lesswrong.com/posts/qtdSzLpQ8BXv6YANd/in-context-learning-of-representations-can-be-explained-by
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
View all episodes
By LessWrongThis is a crosspost of my ICLR 2026 blogpost track post. All code and experiments are available at github.com/andyrdt/iclr_induction.
Summary
Park et al., 2025 show that when large language models (LLMs) process random walks on a graph, their internal representations come to mirror the underlying graph's structure. The authors interpret this broadly, suggesting that LLMs can "manipulate their representations in order to reflect concept semantics specified entirely in-context". In this post, we take a closer look at the underlying mechanism, and suggest a simpler explanation. We argue that induction circuits (Elhage et al., 2021; Olsson et al., 2022), a well-known mechanism for in-context bigram recall, suffice to explain both the task performance and the representation geometry observed by Park et al.
Recapitulation and reproduction of Park et al., 2025
We begin by describing the experimental setup of Park et al., 2025 and reproducing their main results on Llama-3.1-8B.
Figure 1. Overview of Park et al.(a) The grid tracing task uses a 4×4 grid of words. (b) Models observe random walks on the grid (e.g., apple bird milk sand sun plane opera ...) where consecutive words are always neighbors. As the sequence length grows, the model begins to predict valid [...]
---
Outline:
(00:20) Summary
(01:06) Recapitulation and reproduction of Park et al., 2025
(02:03) The grid tracing task
(04:36) Reproduction and Park et al.s interpretation
(06:19) A simpler explanation: induction circuits
(07:32) Testing the induction hypothesis
(08:45) Results
(11:25) Previous-token mixing can account for representation geometry
(11:52) The neighbor-mixing hypothesis
(12:50) A toy model of previous-token mixing
(13:56) Evidence of neighbor mixing in individual model activations
(15:34) Limitations
(17:57) Conclusion
The original text contained 4 footnotes which were omitted from this narration.
---
First published:
March 2nd, 2026
Source:
https://www.lesswrong.com/posts/qtdSzLpQ8BXv6YANd/in-context-learning-of-representations-can-be-explained-by
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
More shows like LessWrong (30+ Karma)
View all
The Daily
113,290 Listeners
Astral Codex Ten Podcast
132 Listeners
Interesting Times with Ross Douthat
7,259 Listeners
Dwarkesh Podcast
566 Listeners
The Ezra Klein Show
16,498 Listeners
AI Article Readings
4 Listeners
Doom Debates!
14 Listeners
LessWrong posts by zvi
2 Listeners