INDEX

Explanations

terms related to surgical risk and postoperative complications

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

Statistical analysis and patient data

np_acts-logits-general · gemini-2.0-flash

statistical analysis variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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



-0.45

culosis

-0.45

 typically

-0.45

 oftentimes

-0.44

 triliun

-0.44

**********/

-0.43

 leadership

-0.43

 bilhões

-0.42

 normalmente

-0.42

//</

-0.42

POSITIVE LOGITS

 незавершена

0.89

parsedMessage

0.79

DoubleQuotes

0.70

mogorov

0.69

InitVars

0.69

 Logistic

0.65

 esternos

0.64

 Subjects

0.62

 median

0.62

median

0.60

Activations Density 3.921%

terms related to surgical risk and postoperative complications

Statistical analysis and patient data

statistical analysis variables

No Comments

No Known Activations