INDEX

Explanations

references to scientific or medical laboratory terminology

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

containing "lab", "Hab", "Rab", or "Tab"

np_acts-logits-general · gemini-2.0-flash

lab, tab, rabies

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Personensuche

-0.77

 Coppola

-0.67

UserScript

-0.66

ſelves

-0.66

mtable

-0.66

 Parthen

-0.64

//

-0.64

 Diony

-0.64

msubsup

-0.63

 Coimbra

-0.63

POSITIVE LOGITS

Lab

0.99

Lab

0.93

lab

0.87

 labs

0.84

lab

0.83

 Labs

0.76

LAB

0.75

labor

0.71

tab

0.68

 LABOR

0.67

Activations Density 0.160%

references to scientific or medical laboratory terminology

containing "lab", "Hab", "Rab", or "Tab"

lab, tab, rabies

No Comments

No Known Activations