INDEX

Explanations

terms related to medical treatments and drug trials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Roskov

-0.85

########.

-0.80

CloseOperation

-0.74

 հղումներ

-0.72

HasAnnotation

-0.71

bonucleic

-0.71

 كمان

-0.68

GraphicsUnit

-0.66

脚注の使い方

-0.64

ⓘ

-0.64

POSITIVE LOGITS

hiker

0.47

0.43

ModelAdmin

0.43

省市镇

0.42

 CURIAM

0.35

ForeignKey

0.35

hips

0.34

or

0.34

tagHelperRunner

0.34

DataAnnotations

0.34

Activations Density 2.029%

terms related to medical treatments and drug trials

No Comments

No Known Activations