INDEX

Explanations

expressions of ownership and individuality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

er

-0.72

 faptul

-0.71

 novità

-0.70

 culoare

-0.67

 navideño

-0.60

 tuturor

-0.58

året

-0.58

ically

-0.58

 involucrados

-0.58

 nedeniyle

-0.58

POSITIVE LOGITS

own

1.56

Own

1.34

OWN

1.33

Own

1.27

own

1.14

 sendiri

1.06

 eigenen

1.02

 соб

0.97

OWN

0.95

 personal

0.91

Activations Density 0.064%

expressions of ownership and individuality

No Comments

No Known Activations