INDEX

Explanations

words related to art, travel, dining and entertainment

oai_token-act-pair · gemini-2.0-flash

Fans and Lovers

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

 beginnetje

-0.52

NewUrlParser

-0.51

 fubject

-0.42

 cauſe

-0.42

 caufe

-0.42

rungsseite

-0.42

 chio

-0.40

ík

-0.38

 profit

-0.38

chise

-0.38

POSITIVE LOGITS

 fans

2.48

 lovers

2.20

 Fans

2.14

fans

2.09

Fans

2.06

fan

2.05

 lover

1.95

 enthusiasts

1.90

lovers

1.82

 Lovers

1.77

Activations Density 1.356%

words related to art, travel, dining and entertainment

Fans and Lovers

No Comments

No Known Activations