INDEX

Explanations

mentions of personal relationships and emotional connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

her

-1.26

她的

-0.94

 hennes

-0.82

 ее

-0.75

 hers

-0.70

 hendes

-0.69

 её

-0.69

 haar

-0.66

彼女の

-0.65

herself

-0.63

POSITIVE LOGITS

she

2.27

 она

1.34

 вона

1.09

 hän

0.93

zij

0.89

 היא

0.83

She

0.81

she

0.76

Она

0.70

ona

0.67

Activations Density 0.266%

mentions of personal relationships and emotional connections

No Comments

No Known Activations