INDEX

Explanations

references to healthcare interactions and guidance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ьаж

-0.65

 Technicians

-0.60

 parishi

-0.59

 ExecuteAsync

-0.58

Singer

-0.58

 Schüler

-0.58

 golfers

-0.56

 PLAYERS

-0.56

 élève

-0.53

Athlete

-0.53

POSITIVE LOGITS

 coach

0.78

 minder

0.72

 trainer

0.69

 instructor

0.68

 trusted

0.67

 supervising

0.66

 mentor

0.65

 guide

0.63

 supervisor

0.63

 facilitator

0.62

Activations Density 0.367%

references to healthcare interactions and guidance

No Comments

No Known Activations