> ## Documentation Index
> Fetch the complete documentation index at: https://notes.kodekloud.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Visualizing Learned Concepts in LLM Representations

> Guidance on using UMAP and t-SNE to visualize semantic clusters in LLM embedding spaces.

Question 5.

When analyzing the output of a transformer-based language model, which technique would be most effective for visualizing the relationship between different concepts in the model's learned representations?

Options: [t-SNE](https://scikit-learn.org/stable/modules/generated/sklearn.manifold.TSNE.html) or [UMAP](https://umap-learn.readthedocs.io/en/latest/) dimensionality reduction, bar charts of token frequencies, time series analysis, or cumulative distribution functions?

Answer: [t-SNE](https://scikit-learn.org/stable/modules/generated/sklearn.manifold.TSNE.html) or [UMAP](https://umap-learn.readthedocs.io/en/latest/) dimensionality reduction.

These nonlinear dimensionality-reduction techniques are the most effective ways to visualize relationships between concepts in high-dimensional embedding spaces. They project high-dimensional token or sentence embeddings into 2D or 3D while preserving neighborhood (local) relationships, enabling inspection of semantic similarity, clustering, and concept separation.

<Callout icon="lightbulb" color="#1CB2FE">
  Use [UMAP](https://umap-learn.readthedocs.io/en/latest/) or [t-SNE](https://scikit-learn.org/stable/modules/generated/sklearn.manifold.TSNE.html) to explore semantic clusters in embedding spaces. For exploratory visualization, UMAP is typically faster and preserves more global structure; t-SNE often produces clearer local clusters but can be slower and requires careful tuning of perplexity.
</Callout>

Why t-SNE / UMAP are preferred over the other listed options

* Bar charts of token frequencies: show token counts and distributional properties of the corpus, but do not capture geometric relationships in embedding space.
* Time series analysis: suited to temporal trends and sequence behavior, not spatial neighborhood structure in vector embeddings.
* Cumulative distribution functions (CDFs): summarize similarity-score distributions, but cannot reveal cluster topology or neighborhood relationships.

Comparison table

| Technique   |                                  What it reveals | Best use case                                                      |
| ----------- | -----------------------------------------------: | ------------------------------------------------------------------ |
| t-SNE       |  Local neighborhood structure and tight clusters | Small-to-moderate embedding sets where local clustering is primary |
| UMAP        |   Local + more global structure, faster at scale | Exploratory visualization of larger embedding sets; good default   |
| Bar charts  |                    Token frequency distributions | Corpus analysis and preprocessing checks                           |
| Time series |                       Temporal trends in metrics | Sequence/temporal model diagnostics                                |
| CDFs        | Distribution summaries (e.g., similarity scores) | Statistical summaries and threshold selection                      |

Practical recommendations

* Preprocess embeddings: standard scale and optionally apply PCA (e.g., to 50 dims) before UMAP/t-SNE to speed computation and reduce noise.
* Choose the right tool:
  * UMAP: usually the default—faster, scales well, preserves more global relationships.
  * t-SNE: useful when you need very clear local clusters; requires careful hyperparameter tuning.
* Reproducibility: set random seeds—both UMAP and t-SNE are stochastic.
* Visual cues: color points by label, token type, cluster assignment, or model-derived scores (e.g., attention weight or prediction confidence) to make semantic structure obvious.

Example workflow (high-level)

1. Compute or load embeddings (one vector per token/sentence).
2. Optionally apply PCA to reduce to \~50 dimensions.
3. Fit UMAP or t-SNE to 2D/3D.
4. Plot with colors/markers reflecting labels or cluster assignments.

Example: PCA + UMAP

```python theme={null}
import numpy as np
from sklearn.decomposition import PCA
import umap
import matplotlib.pyplot as plt

# X: numpy array of shape (n_samples, n_features) containing embeddings
# 1) PCA preprocessing to speed up and denoise (optional but recommended)
pca = PCA(n_components=50, random_state=42)
X_pca = pca.fit_transform(X)

# 2) UMAP projection to 2D
reducer = umap.UMAP(n_components=2, n_neighbors=15, min_dist=0.1, random_state=42)
X_umap = reducer.fit_transform(X_pca)

# 3) Plot
plt.figure(figsize=(8, 6))
scatter = plt.scatter(X_umap[:, 0], X_umap[:, 1], c=labels, cmap="Spectral", s=5)
plt.title("UMAP projection of embeddings")
plt.xlabel("UMAP 1")
plt.ylabel("UMAP 2")
plt.colorbar(scatter, label="label")
plt.show()
```

Example: PCA + t-SNE

```python theme={null}
from sklearn.manifold import TSNE
from sklearn.decomposition import PCA
import matplotlib.pyplot as plt

# 1) PCA to 50 dims
pca = PCA(n_components=50, random_state=42)
X_pca = pca.fit_transform(X)

# 2) t-SNE projection to 2D
tsne = TSNE(n_components=2, perplexity=30, learning_rate=200, n_iter=1000, random_state=42)
X_tsne = tsne.fit_transform(X_pca)

# 3) Plot
plt.figure(figsize=(8, 6))
scatter = plt.scatter(X_tsne[:, 0], X_tsne[:, 1], c=labels, cmap="Spectral", s=5)
plt.title("t-SNE projection of embeddings")
plt.xlabel("t-SNE 1")
plt.ylabel("t-SNE 2")
plt.colorbar(scatter, label="label")
plt.show()
```

Hyperparameter tips

* t-SNE:
  * `perplexity`: typically 5–50. Smaller values emphasize very local structure; larger values reveal broader groupings.
  * `learning_rate`: often between 100 and 1000.
  * `n_iter`: at least 500–1000; more iterations can improve stability.
* UMAP:
  * `n_neighbors`: controls local vs. global structure (small → very local, large → more global). Typical values: 5–50.
  * `min_dist`: controls how tightly points are packed (lower → tighter clusters).

Interpretation guidance

* Look for coherent clusters where semantically similar tokens/sentences are near each other.
* Use colors/markers for known labels (e.g., POS tags, concept labels, or predicted classes) to validate semantic separation.
* Beware of over-interpreting absolute distances—UMAP/t-SNE emphasize relative neighborhood relationships, not exact metric preservation.
* Validate clusters quantitatively (e.g., silhouette score, cluster purity) rather than relying solely on visual appearance.

<Callout icon="warning" color="#FF6B6B">
  t-SNE and UMAP are stochastic. To ensure reproducibility and comparability, set `random_state`/seed, log hyperparameters (e.g., `perplexity`, `n_neighbors`, `min_dist`), and, when appropriate, run multiple seeds to check stability.
</Callout>

Summary

* For visualizing relationships between concepts in LLM learned representations, prefer UMAP or t-SNE, with UMAP as a practical default for exploratory work and larger datasets.
* Combine dimensionality reduction with preprocessing (PCA), color/annotate points by labels or scores, and validate findings with quantitative metrics.

Links and references

* [UMAP documentation](https://umap-learn.readthedocs.io/en/latest/)
* [t-SNE (scikit-learn)](https://scikit-learn.org/stable/modules/generated/sklearn.manifold.TSNE.html)
* [PCA (scikit-learn)](https://scikit-learn.org/stable/modules/generated/sklearn.decomposition.PCA.html)

<CardGroup>
  <Card title="Watch Video" icon="video" cta="Learn more" href="https://learn.kodekloud.com/user/courses/nvidia-generative-ai-llms-associate-certification/module/b8ad33c7-78ce-4828-a30c-4a8fc01d1781/lesson/21e82dab-3f67-4258-8dfc-d42f13a42249" />
</CardGroup>