INDEX

Explanations

mentions of people, especially their names and titles, sometimes in the context of relationships

oai_token-act-pair · gemini-2.0-flash

unstructured code or markup elements

np_token-act-pair-logits · gpt-4o-mini

Publications/records

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

redning

-0.49

 Eisenberg

-0.42

herzog

-0.42

 woman

-0.42

 roleId

-0.42

 muzzle

-0.41

otoro

-0.41

Woman

-0.40

 Жен

-0.40

 templado

-0.40

POSITIVE LOGITS

rrggbb

0.82

帖最后由

0.70

>");

0.67

Enllaces

0.67

 intptr

0.66

 CreateTagHelper

0.64

 Signalez

0.63

 ControllerBase

0.61

 Référence

0.61

cshtml

0.60

Activations Density 0.357%

mentions of people, especially their names and titles, sometimes in the context of relationships

unstructured code or markup elements

Publications/records

No Comments

No Known Activations