INDEX

Explanations

first-person pronouns and their usage in a context of self-reference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 tuyến

-0.41

"");

-0.36

Trọng

-0.35

练

-0.33

exp

-0.33

the

-0.32

ly

-0.30

bibfield

-0.30

 prepar

-0.30

sqrt

-0.30

POSITIVE LOGITS

 المعيارى

0.80

 يتيمه

0.77

+#+#

0.75

bootstrapcdn

0.73

selves

0.72

NameInMap

0.71

IntoConstraints

0.71

 ſich

0.69

nodoc

0.69

contentLoaded

0.69

Activations Density 0.282%

first-person pronouns and their usage in a context of self-reference

No Comments

No Known Activations