INDEX

Explanations

references to books, media, or notable individuals

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

preceding a time period or a measurement

np_acts-logits-general · gemini-2.0-flash

temporal indicators

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

was

-0.54

Years

-0.54

 Years

-0.53

 Jahre

-0.52

 years

-0.52

那时候

-0.49

 altijd

-0.49

 jaren

-0.48

 yıllar

-0.48

当時は

-0.48

POSITIVE LOGITS

 currently

1.43

currently

1.37

 Currently

1.24

 presently

1.22

Currently

1.21

 đang

1.15

 lately

1.08

目前

1.07

 bislang

1.05

 bisher

1.04

Activations Density 0.567%

references to books, media, or notable individuals

preceding a time period or a measurement

temporal indicators

No Comments

No Known Activations