INDEX

Explanations

personal pronouns reflecting individual or group identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

expandindo

-1.13

 kasarigan

-1.06

 متعلقه

-0.88

Hentet

-0.83

featureID

-0.82

InjectAttribute

-0.81

 resourceCulture

-0.80

 ligiloj

-0.79

afficheront

-0.78

RegressionTest

-0.76

POSITIVE LOGITS

He

0.67

He

0.65

We

0.59

he

0.55

Our

0.55

We

0.51

ोंने

0.50

Our

0.49

he

0.49

She

0.48

Activations Density 0.404%

personal pronouns reflecting individual or group identity

No Comments

No Known Activations