INDEX

Explanations

technical terms and scientific references related to medical trials or studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

sidemargin

-0.60

stahl

-0.54

 Biele

-0.54

alyptus

-0.50

 Haupt

-0.49

entant

-0.49

舎

-0.48

 Valdés

-0.48

╚

-0.47

 medu

-0.46

POSITIVE LOGITS

 AssemblyCulture

1.01

 propOrder

0.65

ParallelGroup

0.62

 jsPsych

0.62

astéroïdes

0.62

+#+#

0.61

 kasarigan

0.60

Intu

0.59

Ron

0.58

WG

0.58

Activations Density 2.293%

technical terms and scientific references related to medical trials or studies

No Comments

No Known Activations