INDEX

Explanations

references to familial relationships and personal 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 himself

-0.93

himself

-0.78

 koji

-0.77

 који

-0.74

 Himself

-0.73

AndEndTag

-0.69

くん

-0.65

 său

-0.61

 męski

-0.61

くんの

-0.60

POSITIVE LOGITS

 herself

1.61

herself

1.11

 bint

0.96

she

0.89

 actress

0.80

 shes

0.80

حياتها

0.75

 goddess

0.74

 powinna

0.74

 businesswoman

0.73

Activations Density 1.977%

references to familial relationships and personal identities

No Comments

No Known Activations