INDEX

Explanations

times, especially regarding broadcast schedules

oai_token-act-pair · gemini-2.0-flash

occurrences of the word "on"

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

on

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

AndEndTag

-0.85

 Мексичка

-0.66

 للمعارف

-0.64

AddHtmlAttribute

-0.62

Portail

-0.62

vernight

-0.61

BeginContext

-0.59

Tembelea

-0.59

IMPORTED

-0.57

Personendaten

-0.56

POSITIVE LOGITS

on

1.95

On

1.15

On

1.10

on

0.89

ON

0.87

 на

0.77

 على

0.75

 pada

0.75

オン

0.72

ona

0.70

Activations Density 2.081%

times, especially regarding broadcast schedules

occurrences of the word "on"

on

No Comments

No Known Activations

times, especially regarding broadcast schedules

occurrences of the word "on"

on

No Comments

No Known Activations