Spaces:
Running
Running
mindchain commited on
Commit ·
e1eac63
1
Parent(s): a15826a
Add Gemma Scope 2 + Neuronpedia Discovery/Steering/Freezing Skills
Browse files- index.html +35 -4
index.html
CHANGED
|
@@ -158,13 +158,44 @@ Plus im Gateway: GitHub, Sentry, Z-Image, Web-Search, Browser Automation
|
|
| 158 |
|
| 159 |
<strong>Die Kombination:</strong> Ralph liefert die Schleife, Beads das Gedächtnis, HF Skills das Lernen.
|
| 160 |
|
| 161 |
-
|
| 162 |
-
|
| 163 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 164 |
<a href="https://github.com/anthropics/claude-code/tree/main/plugins/ralph-wiggum" class="link">Ralph Wiggum GitHub</a>
|
| 165 |
<a href="https://github.com/steveyegge/beads" class="link">Beads GitHub</a>
|
| 166 |
<a href="https://github.com/huggingface/skills" class="link">HF Skills GitHub</a>
|
| 167 |
-
<a href="https://huggingface.co/blog/hf-skills-training" class="link">HF Skills Blog</a
|
|
|
|
|
|
|
| 168 |
</div>
|
| 169 |
|
| 170 |
<div class="post">
|
|
|
|
| 158 |
|
| 159 |
<strong>Die Kombination:</strong> Ralph liefert die Schleife, Beads das Gedächtnis, HF Skills das Lernen.
|
| 160 |
|
| 161 |
+
<strong>5. Gemma Scope 2 + Neuronpedia (Interpretability + Steering)</strong>
|
| 162 |
+
Das Agent-Training wird transparent und steuerbar.
|
| 163 |
+
|
| 164 |
+
<span style="color: #667eea;">Discovery Skills</span> - WAS lernt der Agent?
|
| 165 |
+
• SAE Features finden die das Verhalten bestimmen
|
| 166 |
+
• Circuits identifizieren (Kausal-Ketten im Netzwerk)
|
| 167 |
+
• Neuronpedia: 4TB+ activations, explanations, metadata
|
| 168 |
+
• <a href="https://www.neuronpedia.org/gemma-scope-2" class="link">neuronpedia.org/gemma-scope-2</a>
|
| 169 |
+
|
| 170 |
+
<span style="color: #667eea;">Steering Skills</span> - Verhalten beeinflussen
|
| 171 |
+
• Feature-Stärke erhöhen/verringern (↑/↓)
|
| 172 |
+
• API: POST /api/steer mit strength_multiplier
|
| 173 |
+
• "Golden Gate Claude" aber für jeden Feature
|
| 174 |
+
• <a href="https://docs.neuronpedia.org/steering" class="link">Neuronpedia Steering Docs</a>
|
| 175 |
+
|
| 176 |
+
<span style="color: #667eea;">Freezing Skills</span> - Gelerntes fixieren
|
| 177 |
+
• Wichtige Circuits identifizieren und speichern
|
| 178 |
+
• Feature-Vektoren exportieren und wiederverwenden
|
| 179 |
+
• Agent-Verhalten konsistent halten
|
| 180 |
+
• <a href="https://github.com/hijohnnylin/neuronpedia-python" class="link">neuronpedia-python GitHub</a>
|
| 181 |
+
|
| 182 |
+
<strong>Der erweiterte Loop:</strong>
|
| 183 |
+
1. Ralph startet → Agent führt Task aus
|
| 184 |
+
2. Beads tracked → Graph speichert Fortschritt
|
| 185 |
+
3. Gemma Scope 2 → Activations werden analysiert
|
| 186 |
+
4. Neuronpedia → Discovery: Wichtige Features finden
|
| 187 |
+
5. Steering → Agent-Verhalten aktiv korrigieren
|
| 188 |
+
6. HF Skills → Gelerntes in Model trainieren
|
| 189 |
+
7. Freezing → Erfolgreiche Patterns fixieren
|
| 190 |
+
8. Loop wiederholt → Verbesserter Agent
|
| 191 |
+
|
| 192 |
+
<strong>Links:</strong>
|
| 193 |
<a href="https://github.com/anthropics/claude-code/tree/main/plugins/ralph-wiggum" class="link">Ralph Wiggum GitHub</a>
|
| 194 |
<a href="https://github.com/steveyegge/beads" class="link">Beads GitHub</a>
|
| 195 |
<a href="https://github.com/huggingface/skills" class="link">HF Skills GitHub</a>
|
| 196 |
+
<a href="https://huggingface.co/blog/hf-skills-training" class="link">HF Skills Blog</a>
|
| 197 |
+
<a href="https://www.neuronpedia.org/api-doc" class="link">Neuronpedia API</a>
|
| 198 |
+
<a href="https://deepmind.google/blog/gemma-scope-2" class="link">Gemma Scope 2 DeepMind</a></div>
|
| 199 |
</div>
|
| 200 |
|
| 201 |
<div class="post">
|