INDEX

Explanations

references to time or temporal elements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

following "time"

np_acts-logits-general · gemini-2.0-flash

time series, synchronization, points

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

Negative Logits

脚注の使い方

-1.04

-0.65

HtmlAttribute

-0.64

niająca

-0.62

 يتيمه

-0.61

ibol

-0.58

 Besøkt

-0.56

fällig

-0.56

WebServlet

-0.56

tanleria

-0.56

POSITIVE LOGITS

aarrggbb

0.63

 series

0.56

 domain

0.55

 stepped

0.52

 stamps

0.52

معلومات

0.52

 step

0.50

 stamping

0.49

 since

0.49

domain

0.49

Activations Density 0.179%

references to time or temporal elements

following "time"

time series, synchronization, points

No Known Activations