INDEX

Explanations

phrases and terms that reference the concept of "multiple."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 cerebellum

-0.76

itinéraire

-0.73

 thiệu

-0.72

 Burbank

-0.71

 cigars

-0.70

il

-0.68

 carina

-0.68

 placée

-0.68

iness

-0.67

 interesan

-0.66

POSITIVE LOGITS

 multiple

1.06

tiple

1.01

 MULTIPLE

0.94

Multiple

0.93

 Multiple

0.92

ividual

0.92

MULTIPLE

0.91

++++++++++++++++

0.90

multiple

0.89

]='\

0.83

Activations Density 0.100%

phrases and terms that reference the concept of "multiple."

No Comments

No Known Activations