INDEX

Explanations

phrases and terms related to dosage and medication instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

 autorytatywna

-0.58

SourceChecksum

-0.51

 chré

-0.42

 chrétiens

-0.41

modb

-0.40

HtmlAttribute

-0.40

zzá

-0.39

 métiers

-0.39

tehen

-0.38

 convite

-0.37

POSITIVE LOGITS

 dose

1.12

 doses

1.09

 dosage

1.05

 daily

1.00

 dosages

0.96

 dosing

0.95

dose

0.93

Dose

0.88

 dosis

0.87

 Dose

0.87

Activations Density 1.150%

phrases and terms related to dosage and medication instructions

No Comments

No Known Activations