INDEX

Explanations

terms related to medical or healthcare contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

—

-0.70

 linkovi

-0.65

 autorytatywna

-0.63

expandindo

-0.63

rungsseite

-0.63

NewReader

-0.63

İstinadlar

-0.62

 Administrativna

-0.62

WireFormatLite

-0.62

 nonatomic

-0.61

POSITIVE LOGITS

MED

0.65

 medu

0.65

Med

0.63

 Medford

0.63

Med

0.62

 Medi

0.58

sendRedirect

0.55

httphttps

0.51

 medi

0.50

Medi

0.50

Activations Density 0.113%

terms related to medical or healthcare contexts

No Comments

No Known Activations