INDEX

Explanations

words related to response and/or action

oai_token-act-pair · gemini-2.0-flash

interference and response

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

 nahilalakip

-0.85

RectangleBorder

-0.82

enumi

-0.78

MigrationBuilder

-0.76

ReusableCell

-0.73

帖最后由

-0.71

Бахар

-0.68

 ویکی‌پدی

-0.66

InputBorder

-0.66

 Normdatei

-0.63

POSITIVE LOGITS

########.

0.52

 Itself

0.49

nestjs

0.44

 myſelf

0.44

 faſt

0.44

Enfin

0.43

 Celui

0.43

 initComponents

0.42

themselves

0.42

 duquel

0.42

Activations Density 6.871%

words related to response and/or action

interference and response

No Comments

No Known Activations