← Back to 20260211 Archive

Experiment Dashboard: Boolean Automaton & Total Interpretation

Visualizations of Q1-Q4 results, bit leverage, margin analysis, and neuron contributions

Bit Leverage Hierarchy (300:52:1)

Sign
0.046
KL/bit
Exponent
0.008
KL/bit
Mantissa
0.00015
KL/bit

Dynamics Mode BPC Comparison

Sign-only (128-bit Boolean): 5.690 bpc — BETTER than full f32

Pre-activation Margin Distribution

Mean Margin
60.5
|z| > 1.0
98.9%
|z| < 0.1
0.1%

Gradient Decorrelation with Depth

f32 gradient mantissa: 0.7/23 bits agreement at d=1. By d=11, all channels zero.

Q3: Neuron Contribution to Compression

h28 alone
99.7%
of compression gap
Top 15
102.0%
beats full model
Max mantissa
0.002
bpc contribution
Full BPC
4.965
all 128 neurons

Q2: RNN Offset Utilization

MI-greedy [1,3,8,20] captures only 9.4% of sign-change signal. RNN uses d=18-25.

Q4: Neuron Volatility & Co-flip Groups

Volatile
128/128
Dwell Time
3.3
steps
Sign Changes
31.6
per step

Boolean Influence Graph Properties

W_h Fan-in
125/128
dense weights
Boolean Out-degree
3.5
mean
Top Edge
h111→h49
strength 0.282
Unique States
520/520
all positions unique
Dense weights (fan-in 125) but sparse Boolean influence (out-degree 3.5). Large margins absorb most perturbations. No attractors, no cycles up to period 100.

Pattern Ranking: f32 vs Exact

Spearman rank correlation reaches 1.000 at d≥11. Zero phantom patterns.

f32 Error Ratio Over Time

Error ratio locks to 3.44 at t=42 (transient), then 1.0 at steady state (t>60).