INDEX

Explanations

references to the first-person possessive pronoun "my"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CloseOperation

-0.94

 yourselves

-0.85

 Himself

-0.80

 themselves

-0.79

SpringBootTest

-0.77

themselves

-0.77

 nostru

-0.76

 uska

-0.75

 conosco

-0.73

 nous

-0.73

POSITIVE LOGITS

 myself

1.25

my

1.15

am

0.97

my

0.90

myself

0.89

 personally

0.84

 Myself

0.76

 mijn

0.76

 moje

0.73

My

0.71

Activations Density 0.114%

references to the first-person possessive pronoun "my"

No Comments

No Known Activations