INDEX

Explanations

terms related to health conditions and diseases

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

migrationBuilder

-0.53

 Kannada

-0.52

ngdoc

-0.51

 Baillargeon

-0.48

 diser

-0.47

rassed

-0.46



-0.45

çants

-0.45

AntiForgeryToken

-0.45

 références

-0.45

POSITIVE LOGITS

 worldwide

2.87

 global

2.81

 globally

2.61

global

2.51

worldwide

2.50

 international

2.50

 weltweit

2.34

 mundial

2.29

Worldwide

2.23

 Worldwide

2.22

Activations Density 0.747%

terms related to health conditions and diseases

No Comments

No Known Activations