INDEX

Explanations

phrases indicating something that is acknowledged or established as factual or recognized

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

"known" followed by "to" or other prepositions

np_acts-logits-general · gemini-2.0-flash

known properties

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

upol

-0.47

parity

-0.46

 opti

-0.46

pellier

-0.46

pelier

-0.45

gadget

-0.45

spider

-0.44

Parity

-0.44

 Beatty

-0.43

batterie

-0.43

POSITIVE LOGITS

 known

2.19

 Known

2.16

Known

2.05

known

1.99

 KNOWN

1.95

KNOWN

1.73

 conocida

1.52

 conocido

1.50

 connus

1.44

 conocidos

1.41

Activations Density 0.166%

phrases indicating something that is acknowledged or established as factual or recognized

"known" followed by "to" or other prepositions

known properties

No Comments

No Known Activations