INDEX

Explanations

terms related to medical or healthcare contexts, particularly focusing on patient and healthcare provider interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 '\\;'

-1.04

脚注の使い方

-0.92

RectangleBorder

-0.89

 Мексичка

-0.87

HostException

-0.86

出版年

-0.82

存于互联网档案馆

-0.79

 NSCoder

-0.79

WebVitals

-0.79

 Biôgrafia

-0.79

POSITIVE LOGITS

3.19

2.19

／

1.74

/(

1.69

-/

1.67

/-

1.60

/"

1.51

/.

1.51

/_

1.50

/\

1.49

Activations Density 0.685%

terms related to medical or healthcare contexts, particularly focusing on patient and healthcare provider interactions

No Comments

No Known Activations