INDEX

Explanations

specific terms related to medical settings, such as hospitals and emergency services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cader

-0.46

NameInMap

-0.44

tbx

-0.43

 للاسماء

-0.42

 CreateTagHelper

-0.42

cador

-0.42

cetti

-0.42

 protoimpl

-0.41

rath

-0.40

dagangan

-0.40

POSITIVE LOGITS

jsxFileName

0.50

̈́

0.43

SequentialGroup

0.43

 ujednoznacz

0.40

ModelForm

0.39

SharedDtor

0.39

 diplomas

0.38

énario

0.38

 NSCoder

0.37

homonymie

0.36

Activations Density 0.484%

specific terms related to medical settings, such as hospitals and emergency services

No Comments

No Known Activations