INDEX

Explanations

proper nouns indicating geographic locations

oai_token-act-pair · gemini-2.0-flash

Locations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 County

-1.22

 COUNTY

-1.21

County

-1.16

county

-1.03

 county

-1.03

 Counties

-0.96

 counties

-0.91

COUNTY

-0.91

DeleteBehavior

-0.67

Coun

-0.65

POSITIVE LOGITS

 groaned

0.51

 annexed

0.49

Notae

0.48

 riuscito

0.47

鎮

0.46

WithIOException

0.46

!(

0.45

 urma

0.45

minecraftforge

0.44

Activations Density 1.074%

proper nouns indicating geographic locations

Locations

No Comments

No Known Activations