INDEX

Explanations

negatively-toned phrases related to caring or boredom

oai_token-act-pair · gemini-2.0-flash

indifference

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

<bos>

-0.57

-0.50

 handleMessage

-0.44

-0.42

rau

-0.42

tov

-0.42

ToInt

-0.41

 предпо

-0.40

ift

-0.40

POSITIVE LOGITS

 متعلقه

0.91

MLLoader

0.91

 Мексичка

0.90

Personendaten

0.89

ChildScrollView

0.88

 فريبيس

0.87

SourceChecksum

0.85

TagMode

0.82

 Chwiliwch

0.81

 myſelf

0.79

Activations Density 0.734%

negatively-toned phrases related to caring or boredom

indifference

No Comments

No Known Activations