INDEX

Explanations

terms related to brain regions and anatomical components involved in neurological conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

bosis

-0.48

schrift

-0.46

 embolism

-0.42

ophysical

-0.41

 shouldBe

-0.40

quiao

-0.40

 бор

-0.39

 grie

-0.39

Constru

-0.38

()].

-0.38

POSITIVE LOGITS

 ovaries

0.81

 airports

0.71

 useDispatch

0.70

 autorytatywna

0.70

TestingModule

0.70

 ristoranti

0.68

########.

0.67

 vétérina

0.66

gdala

0.66

region

0.66

Activations Density 0.960%

terms related to brain regions and anatomical components involved in neurological conditions

No Comments

No Known Activations