INDEX

Explanations

references to personal pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 שוליים

-0.88

 itſelf

-0.87

 ligiloj

-0.86

 &___

-0.81

OGND

-0.80

 kasarigan

-0.78

 חיצוניים

-0.76

 autorytatywna

-0.74

 تانيه

-0.72

IndentedString

-0.71

POSITIVE LOGITS

him

0.82

0.74

He

0.63

he

0.60

0.59

He

0.59

to

0.56

</em>

0.56

me

0.56

Activations Density 0.119%

references to personal pronouns

No Comments

No Known Activations