INDEX

Explanations

key terms and titles associated with documents, awards, or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 InputDecoration

-0.74

NOPQRST

-0.63

HasForeignKey

-0.62

efficacité

-0.59

 BoxDecoration

-0.58

 Normdatei

-0.57

 تعدى

-0.57

BuilderFactory

-0.56

unknownFields

-0.55

 tacto

-0.54

POSITIVE LOGITS

homonymie

0.63

 AUSSI

0.56

########.

0.54

äsident

0.53

($)

0.50

nestjs

0.48

 kasarigan

0.48

 Mace

0.47

futbolista

0.46

.$,

0.46

Activations Density 0.307%

key terms and titles associated with documents, awards, or categories

No Comments

No Known Activations