INDEX

Explanations

references to medical institutions and healthcare-related contexts

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

terase

-0.50

 CURIAM

-0.47

("$.

-0.46

дино

-0.45

ArrowToggle

-0.45

DebuggerStep

-0.43

kui

-0.43

 Wohnzimmer

-0.42

 LCCN

-0.41

 famí

-0.40

POSITIVE LOGITS

 hospitals

0.83

 Hospitals

0.76

 hospital

0.75

Hospitals

0.70

 Hospital

0.69

Tembelea

0.64

 AssemblyCompany

0.64

hospital

0.64

Hospital

0.63

hosp

0.63

Activations Density 0.236%

references to medical institutions and healthcare-related contexts

No Comments

No Known Activations