INDEX

Explanations

medical terminology related to patient conditions and evaluations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

poj

-0.42

 souris

-0.41

 effetto

-0.41

 humanos

-0.40

 patrols

-0.39

 finalement

-0.38

بین

-0.38

 humains

-0.38

 responsabili

-0.37

ortun

-0.37

POSITIVE LOGITS

 history

1.43

 previous

1.24

history

1.19

previous

1.14

 past

1.14

 History

1.13

 Previous

1.11

Previous

1.10

 histories

1.08

History

1.05

Activations Density 1.124%

medical terminology related to patient conditions and evaluations

No Comments

No Known Activations