INDEX

Explanations

phrases associated with medical procedures and health-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

PreferredItem

-0.77

KURZBESCHREIBUNG

-0.67

tvguidetime

-0.65

 otomatig

-0.65

dotenv

-0.64

ỏng

-0.63

λίου

-0.60

UnsafeEnabled

-0.59

mtrl

-0.58

IBarButtonItem

-0.58

POSITIVE LOGITS

 admittedly

0.70

 perhaps

0.66

perhaps

0.64

 albeit

0.63

 seemingly

0.62

 quizá

0.60

albeit

0.59

 quizás

0.59

 somewhat

0.57

 arguably

0.57

Activations Density 0.290%

phrases associated with medical procedures and health-related topics

No Comments

No Known Activations