INDEX

Explanations

dynamic and interactive descriptions related to shared experiences or narratives

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

that start questions

np_acts-logits-general · gemini-2.0-flash

how, what, why

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tocin

-0.54

thalam

-0.50

LookAnd

-0.49

 تعدى

-0.49

 Reuter

-0.48

✎

-0.48

 thoại

-0.47

ophenol

-0.46

ейс

-0.46

ktı

-0.45

POSITIVE LOGITS

how

2.15

how

1.59

 what

1.54

 cómo

1.47

why

1.41

what

1.27

 bagaimana

1.25

How

1.24

How

1.20

why

1.16

Activations Density 0.386%

dynamic and interactive descriptions related to shared experiences or narratives

that start questions

how, what, why

No Comments

No Known Activations