INDEX

Explanations

medical and health-related terms, especially those associated with specific conditions and treatments

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

principalTable

-0.83

UIControlState

-0.70

webElementXpaths

-0.68

 gynhyrchwyd

-0.68

="@+

-0.67

 تانيه

-0.67

 utafitiHapana

-0.65

AntiForgeryToken

-0.64

GEBURTSDATUM

-0.64

хіво

-0.61

POSITIVE LOGITS

 ويكيميديا

0.66

 kriti

0.54

NOPQRST

0.52

 UserController

0.52

 electors

0.52

 Uncategorized

0.51

 coughed

0.51

 whor

0.50

 angered

0.49

 Manne

0.49

Activations Density 2.162%

medical and health-related terms, especially those associated with specific conditions and treatments

No Comments

No Known Activations