INDEX

Explanations

key terms related to healthcare and patient care models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Personensuche

-1.09

 financeira

-0.95

expandindo

-0.94

WebElementEntity

-0.82

OGND

-0.80

 disambiguazione

-0.79

########.

-0.77

 inocente

-0.76

 unvaccinated

-0.75

 jurídica

-0.75

POSITIVE LOGITS

 approach

0.74

 model

0.74

 mode

0.68

 models

0.64

 method

0.63

 concept

0.60

 style

0.59

mode

0.57

 concepts

0.56

 Model

0.56

Activations Density 0.476%

key terms related to healthcare and patient care models

No Comments

No Known Activations