INDEX

Explanations

elements related to crime, threats, and hidden identities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

"}")

-0.48

alagi

-0.48

CppMethod

-0.48

Démographie

-0.47

tuj

-0.46

RESS

-0.45

HOLD

-0.45

 beschäf

-0.44

(:,:,

-0.44

TagMode

-0.44

POSITIVE LOGITS

 anonymously

0.89

 anonymous

0.87

 anonyme

0.78

Anonymous

0.74

 Anonymous

0.71

 mystery

0.68

匿名

0.67

 mysterious

0.65

 匿名

0.64

 unidentified

0.63

Activations Density 0.305%

elements related to crime, threats, and hidden identities

No Comments

No Known Activations