INDEX

Explanations

terms related to healthcare, treatment, and patient interactions in medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

RICAL

-0.61

TRAILING

-0.61

 manches

-0.60

menistan

-0.59

urope

-0.55

TagMode

-0.53

 Steck

-0.52

nictví

-0.51

 pylori

-0.51

 Celui

-0.51

POSITIVE LOGITS

 consumers

0.71

 client

0.67

 consumer

0.65

 clients

0.65

Consumers

0.63

 konsumen

0.62

 customers

0.56

consumers

0.56

 Clients

0.55

 Consumers

0.55

Activations Density 0.623%

terms related to healthcare, treatment, and patient interactions in medical contexts

No Comments

No Known Activations