INDEX

Explanations

quantitative expressions indicating small amounts of time

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

"few" followed by a unit of time

np_acts-logits-general · gemini-2.0-flash

few units of time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

mantec

-0.52

vání

-0.51

 totales

-0.47

bridi

-0.47

 suatu

-0.46

 alguna

-0.46

 algún

-0.46

 sesuatu

-0.46

SourceChecksum

-0.45

stuff

-0.45

POSITIVE LOGITS

 hundred

1.63

 dozen

1.48

 thousand

1.37

hundred

1.26

 weeks

1.19

dozen

1.15

thousand

1.09

 months

1.05

 hundert

1.02

 minutes

0.95

Activations Density 0.091%

quantitative expressions indicating small amounts of time

"few" followed by a unit of time

few units of time

No Comments

No Known Activations