INDEX

Explanations

phrases related to medical or biological studies involving patient outcomes, diagnostics, and health metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

IMPORTED

-0.52

uttavia

-0.51

but

-0.47

 platform

-0.47

 Popular

-0.47

-------------</

-0.46

 Portail

-0.46

ък

-0.46

 works

-0.46

ですが

-0.46

POSITIVE LOGITS

 disambiguazione

0.78

ISupport

0.73

 betweenstory

0.69

 ویکی‌پدی

0.65

IsContent

0.63

 Baillargeon

0.62

parsedMessage

0.61

IntoConstraints

0.60

tvguidetime

0.59

yelitis

0.58

Activations Density 0.590%

phrases related to medical or biological studies involving patient outcomes, diagnostics, and health metrics

No Comments

No Known Activations