INDEX

Explanations

terms related to accuracy and precision in measurements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Texts about "accuracy" or being "accurate"

np_acts-logits-general · gemini-2.0-flash

accuracy of measurement and prediction

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nahilalakip

-0.54

 Rodrig

-0.47

 Gual

-0.44

 Weing

-0.44

 Bote

-0.43

 Monteiro

-0.42

 parental

-0.42

 Lein

-0.42

Goy

-0.41

 Merv

-0.41

POSITIVE LOGITS

 accuracy

1.94

 accurate

1.82

accurate

1.80

 Accurate

1.80

Accurate

1.77

 Accuracy

1.76

 ACCUR

1.73

 precision

1.67

Accuracy

1.65

 precisión

1.61

Activations Density 0.280%

terms related to accuracy and precision in measurements

Texts about "accuracy" or being "accurate"

accuracy of measurement and prediction

No Comments

No Known Activations