INDEX

Explanations

medical terms and statistics related to risks and prevalence in health studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Handlung

-0.56

 дописавши

-0.56

ביוגרפיה

-0.55

 ErrIntOverflow

-0.55

PerformLayout

-0.50

 صوتيه

-0.50

ządu

-0.49

ptonshire

-0.48

ysacchar

-0.48

 שוליים

-0.47

POSITIVE LOGITS

 rate

2.39

 rates

2.32

 Rate

2.09

 Rates

2.01

 RATE

1.98

rate

1.96

Rate

1.96

 RATES

1.84

rates

1.80

Rates

1.79

Activations Density 1.038%

medical terms and statistics related to risks and prevalence in health studies

No Comments

No Known Activations