INDEX

Explanations

terms related to healthcare and medical services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ubakar

-0.47

IndentedString

-0.46

 älteren

-0.43

bentar

-0.42

 westfalen

-0.41

 universitarios

-0.41

 Jungen

-0.40

 ältere

-0.39

 çik

-0.38

 mourir

-0.38

POSITIVE LOGITS

 surla

0.66

 informée

0.51

SequentialGroup

0.50

ValueStyle

0.47

standes

0.44

 CURIAM

0.43

ViewImports

0.42

evos

0.42

inds

0.41

Personensuche

0.41

Activations Density 1.205%

terms related to healthcare and medical services

No Comments

No Known Activations