INDEX

Explanations

references to the term "order" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

etheless

-0.97

rachtet

-0.95

++

-0.91

chequer

-0.89

$.

-0.89

wixt

-0.88

duate

-0.87

ificance

-0.87

ratulations

-0.86

^(@)

-0.86

POSITIVE LOGITS

 order

2.69

 Order

2.59

order

2.47

 orders

2.44

 ORDER

2.41

Order

2.39

 Orders

2.29

ORDER

2.25

orders

2.13

Orders

1.97

Activations Density 0.095%

references to the term "order" and its variations

No Comments

No Known Activations