INDEX

Explanations

medical terminology related to conditions, diagnoses, and patient management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

目を

-0.44

SE

-0.41

tare

-0.39

enc

-0.39

there

-0.38

上

-0.38

IE

-0.38

so

-0.37

etsen

-0.37

här

-0.37

POSITIVE LOGITS

 esternos

0.63

 informée

0.63

webElementXpaths

0.62

✨:

0.60

IVEREF

0.60

 surla

0.58

 Wiktionnaire

0.57

Personendaten

0.54

parsedMessage

0.53

OGND

0.52

Activations Density 1.617%

medical terminology related to conditions, diagnoses, and patient management

No Comments

No Known Activations