INDEX

Explanations

terms related to blood and immune responses in transplant settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 correctes

-0.56

 InputDecoration

-0.56

meanor

-0.51

 OFDb

-0.51

 nahilalakip

-0.50

ficação

-0.49

Bertrand

-0.47

toBeDefined

-0.46

زي

-0.46

árqu

-0.45

POSITIVE LOGITS

 donor

1.55

 Donor

1.43

 transplant

1.40

 donors

1.36

Donor

1.36

 transplants

1.31

donor

1.31

 transplantation

1.28

 Transplant

1.28

 DONOR

1.26

Activations Density 0.739%

terms related to blood and immune responses in transplant settings

No Comments

No Known Activations