INDEX

Explanations

terms and phrases related to medical or clinical guidelines and assessments

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

tagHelperRunner

-0.82

 betweenstory

-0.71

новниш

-0.70

bootstrapcdn

-0.70

 سكانية

-0.68

intenant

-0.67

UnusedPrivate

-0.65

webElementXpaths

-0.64

########.

-0.63

":[{

-0.63

POSITIVE LOGITS

TabStop

0.50

란

0.46

そうそう

0.46

Pop

0.45

Glossary

0.44

ass

0.44

lorum

0.44

des

0.41

Diwedd

0.40

chur

0.40

Activations Density 0.686%

terms and phrases related to medical or clinical guidelines and assessments

No Comments

No Known Activations