INDEX

Explanations

time durations and conditions related to specific processes or actions

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

durations of time

np_acts-logits-general · gemini-2.0-flash

durations of time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 hours

-1.01

 Hours

-0.96

 weekend

-0.93

 months

-0.89

 hour

-0.88

Hour

-0.88

hours

-0.87

 weekends

-0.86

 HOURS

-0.86

Hours

-0.86

POSITIVE LOGITS

 seconds

0.75

 moments

0.63

 moment

0.62

issipp

0.62

 Moments

0.61

 brief

0.60

 секунд

0.60

 Sekunden

0.59

 pochi

0.59

few

0.56

Activations Density 0.209%

time durations and conditions related to specific processes or actions

durations of time

durations of time

No Comments

No Known Activations