INDEX

Explanations

terms and phrases related to entities' moral character and behavior

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

出版年

-0.56

 Harding

-0.49

ConnectionString

-0.48

"";

-0.47

TabIndex

-0.46

modi

-0.46

 AspNetCore

-0.46

)';

-0.45

=>

-0.45

platin

-0.44

POSITIVE LOGITS

 interests

0.90

 benefit

0.85

 للمعارف

0.82

 beneficio

0.76

interests

0.75

 intereses

0.74

 Interests

0.73

benefit

0.72

 betterment

0.71

 welfare

0.70

Activations Density 0.329%

terms and phrases related to entities' moral character and behavior

No Comments

No Known Activations