INDEX

Explanations

references to medical symptoms and diagnoses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 potest

-0.62

 habet

-0.57

Comté

-0.57

protoc

-0.56

ethene

-0.56

 pickles

-0.56

ContentAsync

-0.54

 faveur

-0.52

IOUtils

-0.51

 aleación

-0.51

POSITIVE LOGITS

 symptom

1.05

 symptoms

1.02

 diagnosis

0.98

 Symptoms

0.92

 Symptom

0.91

 diag

0.87

diag

0.87

symptoms

0.82

 degradation

0.82

 متعلقه

0.80

Activations Density 0.155%

references to medical symptoms and diagnoses

No Comments

No Known Activations