INDEX

Explanations

phrases related to public meetings and attendance

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

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

hore

-0.51

 esternos

-0.48

 nonatomic

-0.47

lief

-0.47

 CURIAM

-0.46

kiri

-0.46

Locker

-0.44

 出版

-0.43

 veran

-0.42

zle

-0.42

POSITIVE LOGITS

 attendance

2.49

 attend

2.41

 attending

2.31

 attended

2.21

 attends

2.17

 Attending

2.10

 Attend

2.00

 Attendance

1.96

attend

1.91

 ATTEND

1.88

Activations Density 0.300%

phrases related to public meetings and attendance

No Comments

No Known Activations