INDEX

Explanations

terms related to medical or scientific measurements and assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.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

 Keegan

-0.53

CompilerServices

-0.45

 henvisninger

-0.43

 Bigelow

-0.43

Chham

-0.42

jspb

-0.42

elemField

-0.41

Oster

-0.41

béco

-0.41

 TextAlign

-0.40

POSITIVE LOGITS

 McKnight

0.85

 Bryant

0.78

Bryant

0.77

 Alcott

0.75

 Beckett

0.71

 Barnett

0.68

 Rupert

0.68

 Burnett

0.66

 Corbett

0.66

PMT

0.66

Activations Density 1.084%

terms related to medical or scientific measurements and assessments

No Comments

No Known Activations