INDEX

Explanations

terms and phrases related to medical conditions, diagnoses, and the associated statistics

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

","");

-0.50

()][

-0.49

 '').

-0.49

'':

-0.48

tableFuture

-0.47

 deep

-0.45

 space

-0.45

Stamina

-0.44

）.

-0.44

ragend

-0.43

POSITIVE LOGITS

 CreateTagHelper

0.94

 Incidence

0.86

modelBuilder

0.86

出版年

0.85

RenderAtEndOf

0.81

 incidence

0.79

 mortality

0.73

Демографія

0.72

DeleteBehavior

0.71

Deaths

0.71

Activations Density 1.229%

terms and phrases related to medical conditions, diagnoses, and the associated statistics

No Comments

No Known Activations