Feature {feature_index}
- Language: {lang}
- Model: {model}
- Layer: {model_layer}
- SAE Model: {sae_model}
- Selected Token Probability: {selected_prob}
- Entropy: {entropy}
Activation Range
{start}-{end}
Interpretation
{interpretation}
|
Score Type
|
Accuracy
|
Precision
|
Recall |
F1 score
|
TPR |
TNR |
FPR |
FNR |
| {score_type} |
{accuracy} |
{precision} |
{recall} |
{f1_score} |
{true_positive_rate} |
{true_negative_rate} |
{false_positive_rate} |
{false_negative_rate} |
{language}
- #examples: {num_dataset_examples}
{interval}
- Range: {start}-{end}
- #examples: {num_dataset_examples}