INDEX

Explanations

sentences describing someone's mustaches, beard, hair color, or height

oai_token-act-pair · gemini-2.0-flash

must/debe

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 JpaRepository

-0.77

ValueStyle

-0.77

 OMITBAD

-0.76

 jadx

-0.67

 ProtoMessage

-0.64

Бахар

-0.63

ItemBackground

-0.63

 resourceCulture

-0.63

 BoxFit

-0.60

EndInit

-0.59

POSITIVE LOGITS

Must

0.81

 Must

0.79

 must

0.79

must

0.74

MUST

0.68

 MUST

0.67

mou

0.57

 debe

0.55

 Debe

0.53

facial

0.52

Activations Density 0.880%

sentences describing someone's mustaches, beard, hair color, or height

must/debe

No Comments

No Known Activations