INDEX

Explanations

terms related to diagnostic tests and their performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

zocht

-0.58

glBindBuffer

-0.49

IsRequired

-0.46

ma

-0.46

or

-0.46

 spoke

-0.45

Bel

-0.45

lunda

-0.45

marvin

-0.44

HomeAsUpEnabled

-0.44

POSITIVE LOGITS

__":

0.76

 detecting

0.75

adpleegd

0.72

 mxArray

0.70

 eventdata

0.69

ometrics

0.68

 sensors

0.68

TextWatcher

0.68

 instrument

0.67

 InputDecoration

0.67

Activations Density 1.709%

terms related to diagnostic tests and their performance metrics

No Comments

No Known Activations