INDEX

Explanations

specific terms related to data analysis and patient treatment details in medical research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

enumi

-1.07

 MainAxisSize

-0.68

 BoxFit

-0.67

 Exacts

-0.66

 snippetHide

-0.66

ciful

-0.64

 Roskov

-0.64

ItemBackground

-0.63

 Tarn

-0.63

gdx

-0.62

POSITIVE LOGITS

 piú

0.92

0.83

 vnto

0.81

 quæ

0.80

 figliu

0.80

허

0.73

 vostri

0.73

Tembelea

0.71

 zijne

0.70

 Commencez

0.68

Activations Density 3.777%

specific terms related to data analysis and patient treatment details in medical research

No Comments

No Known Activations