INDEX

Explanations

medical terms related to treatments and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

новниш

-0.61

 تضيفلها

-0.58

ėms

-0.57

umą

-0.56

ajuku

-0.55

ėse

-0.55

ėjimo

-0.55

 transférez

-0.54

žiu

-0.51

ių

-0.51

POSITIVE LOGITS

ins

1.47

IN

1.41

ine

1.39

in

1.36

ina

1.34

ines

1.26

INE

1.22

INS

1.18

ined

1.15

ino

1.14

Activations Density 2.038%

medical terms related to treatments and conditions

No Comments

No Known Activations

medical terms related to treatments and conditions

No Comments

No Known Activations