INDEX

Explanations

various connotations of the word "open."

oai_token-act-pair · gemini-2.0-flash

opening

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 quæ

-0.67

 CreateTagHelper

-0.66

multer

-0.66

########.

-0.61

 &___

-0.59

Autoritní

-0.55

 województ

-0.54

icoli

-0.53

 recoil

-0.52

keyColumn

-0.52

POSITIVE LOGITS

 Open

1.35

 open

1.29

 Opens

1.26

 OPEN

1.24

Open

1.24

 closed

1.17

 Closed

1.15

open

1.15

 opened

1.14

 reopen

1.13

Activations Density 0.764%

various connotations of the word "open."

opening

No Comments

No Known Activations