INDEX

Explanations

locations and descriptions related to physical places and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 EconPapers

-0.65

ce

-0.48

 suivants

-0.47

المكان

-0.47

zis

-0.46

rouvez

-0.46

ogramm

-0.46

WRENCE

-0.45

ces

-0.45

#+#

-0.44

POSITIVE LOGITS

 near

2.06

near

1.89

Near

1.53

 Near

1.46

 près

1.42

 outside

1.38

 NEAR

1.36

 utanför

1.27

 dekat

1.25

 outskirts

1.23

Activations Density 0.262%

locations and descriptions related to physical places and events

No Comments

No Known Activations