INDEX

Explanations

mentions of conflicting viewpoints where someone blames another for something.

oai_token-act-pair · gemini-2.0-flash

other

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Others

-1.05

 others

-1.01

Others

-0.92

others

-0.79

InjectAttribute

-0.68

vių

-0.68

 OTHERS

-0.66

resave

-0.60

webElementGuid

-0.59

///</

-0.58

POSITIVE LOGITS

 other

1.42

Other

1.15

 Other

1.13

other

1.13

 OTHER

1.00

OTHER

0.77

 autres

0.71

其他

0.68

 andere

0.66

 otras

0.66

Activations Density 3.837%

mentions of conflicting viewpoints where someone blames another for something.

other

No Comments

No Known Activations