INDEX

Explanations

references to specific individuals or proper nouns

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

after capitalized abbreviations

np_acts-logits-general · gemini-2.0-flash

commelinid, Kaamilya, napus

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Hick

-0.80

 Peck

-0.78

 Franck

-0.77

 peck

-0.76

 Beckett

-0.75

vick

-0.75

icke

-0.75

GAC

-0.74

 Strick

-0.74

JAC

-0.74

POSITIVE LOGITS

 getItemId

0.67

GenerationType

0.56

devamını

0.52

setVerticalGroup

0.48

GeneratedValue

0.48

Brainz

0.48

 transfieras

0.48

atoday

0.47

SpringBootTest

0.47

 تانيه

0.46

Activations Density 0.769%

references to specific individuals or proper nouns

after capitalized abbreviations

commelinid, Kaamilya, napus

No Comments

No Known Activations