INDEX

Explanations

quantitative expressions related to time spans or durations

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

Numbers followed by units of time

np_acts-logits-general · gemini-2.0-flash

numerical time periods

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

:✨

-0.87

 للمعارف

-0.82

rungsseite

-0.80

Times

-0.71

)++;

-0.70

GEBURTSDATUM

-0.69

ïsme

-0.69

 Times

-0.66

labelledby

-0.65

 utafiti

-0.64

POSITIVE LOGITS

 excruciating

0.57

 agonizing

0.56

 frustrating

0.55

 painful

0.53

 harrowing

0.52

 tumultuous

0.52

 arduous

0.52

 solid

0.48

 heartbreaking

0.48

gru

0.48

Activations Density 0.199%

quantitative expressions related to time spans or durations

Numbers followed by units of time

numerical time periods

No Comments

No Known Activations