INDEX

Explanations

terms related to medical diagnosis and diagnostic processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 tetto

-0.65

openhauer

-0.65

 unirse

-0.62

 exportación

-0.61

getc

-0.59

 spørs

-0.59

 toată

-0.57

 proprietà

-0.56

 celda

-0.55

 brukt

-0.55

POSITIVE LOGITS

 diagnose

1.73

 diagnosis

1.63

 diagnoses

1.59

 diagnosing

1.57

 Diagnosis

1.50

 DIAG

1.43

diagnosis

1.42

 Diagnos

1.41

 diagnosed

1.39

 diagnos

1.38

Activations Density 0.100%

terms related to medical diagnosis and diagnostic processes

No Comments

No Known Activations