INDEX

Explanations

statistics and metrics related to health outcomes and clinical trial results

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

Rates of undesirable outcomes

np_acts-logits-general · gemini-2.0-flash

rates of mortality and attrition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 يتيمه

-0.43

 potenti

-0.41

 Vikipedi

-0.40

BagConstraints

-0.37

rangian

-0.36

payee

-0.35

 Potenti

-0.35

CommandText

-0.34

Diwedd

-0.34

AddWithValue

-0.33

POSITIVE LOGITS

 rates

1.50

 rate

1.47

 taux

1.38

 Rates

1.34

 Rate

1.33

Rates

1.24

Rate

1.23

 RATES

1.23

 RATE

1.20

率

1.19

Activations Density 0.743%

statistics and metrics related to health outcomes and clinical trial results

Rates of undesirable outcomes

rates of mortality and attrition

No Comments

No Known Activations