INDEX

Explanations

terms related to medical care and healthcare professionals, particularly in a primary care and psychiatric context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

クタイ

-0.52

 aapt

-0.51

 دع

-0.49

 frappé

-0.49

Izvori

-0.48

WithMany

-0.48

 Estadual

-0.47

 financeira

-0.47

culata

-0.47

shima

-0.47

POSITIVE LOGITS

 physician

1.25

 physicians

1.22

 doctors

1.17

 Physicians

1.14

 Physician

1.08

 doctor

1.04

physician

1.01

 clinics

0.98

 medical

0.98

 clinic

0.97

Activations Density 0.647%

terms related to medical care and healthcare professionals, particularly in a primary care and psychiatric context

No Comments

No Known Activations