INDEX

Explanations

phrases expressing knowledge or awareness

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

"know" followed by a question word or "that"

np_acts-logits-general · gemini-2.0-flash

know followed by about, that, how

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itemId

-0.41

 Somers

-0.40

Ers

-0.40

 itemId

-0.40

 Sommers

-0.39

ser

-0.38

 article

-0.37

bild

-0.36

portlet

-0.36

per

-0.36

POSITIVE LOGITS

Know

1.48

 Know

1.34

know

1.30

KNOW

1.29

Knows

1.27

 know

1.23

 KNOW

1.23

 Knows

1.18

knows

1.15

 Knew

1.14

Activations Density 0.094%

phrases expressing knowledge or awareness

"know" followed by a question word or "that"

know followed by about, that, how

No Comments

No Known Activations