INDEX

Explanations

terms related to strokes and cerebrovascular diseases

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

 déchir

-0.81

-0.78

 femininas

-0.74

 חיצוניים

-0.73

aysia

-0.71

 pauvres

-0.71

 esigen

-0.71

 ögon

-0.70

 élas

-0.68

 désol

-0.68

POSITIVE LOGITS

 stroke

3.39

 Stroke

3.07

 strokes

2.92

stroke

2.92

Stroke

2.83

strokes

2.50

 STRO

2.28

 Strokes

2.27

STROKE

2.21

 stroked

1.99

Activations Density 0.074%

terms related to strokes and cerebrovascular diseases

No Comments

No Known Activations