INDEX

Explanations

phrases or concepts indicating additional information or inclusion

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

utched

-0.69

 Woodford

-0.68

="#"><

-0.66

monary

-0.66

 setOpen

-0.66

()==

-0.66

 canteen

-0.66

 végétale

-0.66

openqa

-0.65

ughty

-0.64

POSITIVE LOGITS

 addition

2.22

addition

1.82

 Addition

1.57

Addition

1.44

 additions

1.36

 tillegg

1.22

Additionally

1.17

 Additionally

1.11

 entanto

1.11

 Additions

1.08

Activations Density 0.147%

phrases or concepts indicating additional information or inclusion

No Comments

No Known Activations

phrases or concepts indicating additional information or inclusion

No Comments

No Known Activations