INDEX

Explanations

references to time, especially related to recent events and ongoing changes

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

Time periods (years, weeks) after a number

np_acts-logits-general · gemini-2.0-flash

time spans in years

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

 للمعارف

-0.75

 päivä

-0.67

WireFormat

-0.66

antaranya

-0.66

 createState

-0.65

sizeCache

-0.65

 disambiguazione

-0.64

migrationBuilder

-0.63

 Week

-0.63

principalColumn

-0.61

POSITIVE LOGITS

 years

3.16

years

2.09

 Years

1.91

Years

1.85

 YEARS

1.84

 años

1.81

 Jahren

1.63

yrs

1.60

 Jahre

1.55

 jaren

1.40

Activations Density 0.339%

references to time, especially related to recent events and ongoing changes

Time periods (years, weeks) after a number

time spans in years

No Comments

No Known Activations