INDEX

Explanations

terms related to disease and health conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

ţion

-0.67

ttino

-0.64

 arşivlendi

-0.64

徨

-0.64

 demur

-0.62

Zet

-0.62

Asser

-0.62

 empiric

-0.62

 Jurí

-0.60

 giovan

-0.60

POSITIVE LOGITS

 diseases

1.43

 disease

1.38

 Diseases

1.25

Diseases

1.22

 Disease

1.20

 DISEASES

1.19

Disease

1.14

 DISEASE

1.09

disease

1.07

diseases

1.06

Activations Density 0.100%

terms related to disease and health conditions

No Comments

No Known Activations