INDEX

Explanations

terms related to healthcare practices and legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 come

-0.54

luent

-0.53

ună

-0.52

-0.50

ousine

-0.48

lüğ

-0.48

Diweddarwch

-0.48

加坡

-0.48

he

-0.48

aned

-0.47

POSITIVE LOGITS

 متعلقه

0.90

elemField

0.73

ViewImports

0.70

igshid

0.69

Efq

0.67

 بيها

0.67

rungsseite

0.67

 Lightboxes

0.67

 Theſe

0.66

usermodel

0.64

Activations Density 0.477%

terms related to healthcare practices and legal contexts

No Comments

No Known Activations