INDEX

Explanations

references to significant political events or figures

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

stars/novae

np_acts-logits-general · gemini-2.0-flash

novae and stars

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

ĵ

-0.56

mybatisplus

-0.55

 informée

-0.52

 layui

-0.52

󠁢

-0.51

 Signalez

-0.51

IntentFilter

-0.50

 Beecher

-0.50

 flooring

-0.50

 intptr

-0.49

POSITIVE LOGITS

 star

0.94

 stars

0.90

 stellar

0.79

 supernova

0.79

 étoiles

0.74

stars

0.74

star

0.73

 bintang

0.72

éto

0.70

 Stars

0.68

Activations Density 0.766%

references to significant political events or figures

stars/novae

novae and stars

No Comments

No Known Activations