INDEX

Explanations

phrases related to medical research and disease connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 NgModule

-0.64

Kaieteur

-0.63

issauga

-0.51

caris

-0.50

مزید

-0.50

tonode

-0.49

!")

-0.47

íritu

-0.46

 oprot

-0.46

 allAfrica

-0.46

POSITIVE LOGITS

how

0.85

ValueStyle

0.79

how

0.73

why

0.71

 kasarigan

0.70

 whether

0.62

MessageOf

0.62

ReusableCell

0.60

why

0.60

its

0.59

Activations Density 0.420%

phrases related to medical research and disease connections

No Comments

No Known Activations