INDEX

Explanations

instances and discussions related to medicine

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ficit

-0.66

httphttps

-0.64

 Albright

-0.60

quisition

-0.60

tvguidetime

-0.57

ρων

-0.56

BorderLayout

-0.56

 honourable

-0.56

 Calvert

-0.56

μμα

-0.55

POSITIVE LOGITS

 medicine

1.00

 Medicine

0.90

Medicine

0.84

medicine

0.84

 MEDICINE

0.83

Record

0.63

 betweenstory

0.63

>-->

0.61

helpers

0.59

ільки

0.59

Activations Density 0.095%

instances and discussions related to medicine

No Comments

No Known Activations