INDEX

Explanations

medical conditions and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

gráficas

-0.41

 žem

-0.40

:✨

-0.40

jewództ

-0.39

 endwhile

-0.39

 AppCompatTheme

-0.38

 epidermis

-0.38

 Skins

-0.38

ispiel

-0.38

rored

-0.37

POSITIVE LOGITS

 tumor

0.66

 benign

0.64

 masses

0.62

 cysts

0.59

 tumour

0.59

 cyst

0.58

 tumors

0.58

 growths

0.56

 Masses

0.55

 tumours

0.54

Activations Density 1.073%

medical conditions and related terminology

No Comments

No Known Activations

medical conditions and related terminology

No Comments

No Known Activations