INDEX

Explanations

phrases related to time and duration

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

Time spans after "last" or "past"

np_acts-logits-general · gemini-2.0-flash

past or last and time units

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

catori

-0.61

outi

-0.56

Obrázky

-0.55

 فريبيس

-0.54

 termica

-0.53

 pozdě

-0.53

存于互联网档案馆

-0.53

RepeatedField

-0.52

 Grom

-0.52

vė

-0.50

POSITIVE LOGITS

PerformLayout

0.86

few

0.86

DoubleQuotes

0.68

few

0.68

enderror

0.68

 couple

0.68

decade

0.66

Aiheesta

0.62

Few

0.59

 month

0.59

Activations Density 0.121%

phrases related to time and duration

Time spans after "last" or "past"

past or last and time units

No Comments

No Known Activations