INDEX

Explanations

references to personal belongings or possessions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 himself

-0.97

 Himself

-0.80

himself

-0.79

 koji

-0.78

 који

-0.68

Jr

-0.65

 Filho

-0.63

くん

-0.61

 الدولى

-0.58

ionado

-0.58

POSITIVE LOGITS

 herself

1.60

herself

1.13

 bint

0.92

she

0.88

 powinna

0.80

 shes

0.79

 lesbian

0.77

 actress

0.76

حياتها

0.76

her

0.76

Activations Density 1.737%

references to personal belongings or possessions

No Comments

No Known Activations