INDEX

Explanations

specific medical or scientific terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 majorité

-0.36

 critères

-0.36

 adentro

-0.35

 general

-0.35

Algemeen

-0.35

発

-0.35

 Allgemeinen

-0.33

 absolument

-0.33

Allgeme

-0.33

 tuturor

-0.33

POSITIVE LOGITS

ScopeManager

0.86

 ब्रेकडाउन

0.81

BeginContext

0.75

MigrationBuilder

0.75

 Roskov

0.68

InjectAttribute

0.68

afficheront

0.63

fjspx

0.63

存于互联网档案馆

0.63

Autoritní

0.63

Activations Density 1.562%

specific medical or scientific terminology

No Comments

No Known Activations