INDEX

Explanations

phrases indicating the passage of time or events occurring in the past

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

 rospy

-0.51

깐

-0.51

 Tacitus

-0.42

 они

-0.41

ุป

-0.40

classNames

-0.39

 Warszawie

-0.39

Matter

-0.38

CAI

-0.38

insee

-0.38

POSITIVE LOGITS

 afar

1.29

 across

1.18

 whence

1.10

 abroad

1.09

 scratch

1.08

within

1.05

 within

1.05

 EconPapers

1.00

across

0.99

 anywhere

0.99

Activations Density 0.369%

phrases indicating the passage of time or events occurring in the past

No Comments

No Known Activations