INDEX

Explanations

references to the concept of time and its significance in various contexts

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

"Time" followed by action words

np_acts-logits-general · gemini-2.0-flash

time spent on activities

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

LookAnd

-0.91

 réglementation

-0.60

 rapides

-0.60

 mukaan

-0.58

 pouvoit

-0.58

 föruts

-0.57

 EconPapers

-0.57

startActivity

-0.56

 kautta

-0.56

 toiminta

-0.56

POSITIVE LOGITS

 spent

0.75

 devoted

0.74

 perfecting

0.63

 away

0.62

expandindo

0.60

 dedicated

0.60

 researching

0.59

 насељу

0.57

spent

0.56

انيف

0.56

Activations Density 0.136%

references to the concept of time and its significance in various contexts

"Time" followed by action words

time spent on activities

No Comments

No Known Activations