INDEX

Explanations

terms related to medical or scientific characterization and condition of subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

setupUi

-0.53

camore

-0.51

acağı

-0.49

pakah

-0.49

 naar

-0.48

MessageOf

-0.47

ronom

-0.47

 TestBed

-0.47

RDONLY

-0.46

 ProtoMessage

-0.46

POSITIVE LOGITS

by

1.41

 oleh

0.94

ValueStyle

0.88

by

0.86

By

0.83

 bởi

0.81

By

0.81

 pela

0.74

 pelas

0.73

bys

0.73

Activations Density 0.406%

terms related to medical or scientific characterization and condition of subjects

No Comments

No Known Activations