INDEX

Explanations

terms related to scientific or medical terminology, particularly focusing on biological elements and their interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Nadia

-0.71

 Matth

-0.67

 Barbar

-0.65

 Louie

-0.63

存于互联网档案馆

-0.62

 Bür

-0.59

 rebu

-0.57

 Nour

-0.56

unciation

-0.56

 Hoover

-0.56

POSITIVE LOGITS

 Cable

0.83

 assignable

0.81

gtx

0.77

cune

0.77

LEP

0.77

gunas

0.76

Shopify

0.75

zusetzen

0.74

 Bole

0.74

elemField

0.73

Activations Density 8.543%

terms related to scientific or medical terminology, particularly focusing on biological elements and their interactions

No Comments

No Known Activations