INDEX

Explanations

the word "us" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 paran

-0.60

cah

-0.52

 Denne

-0.52

 Morte

-0.52

談社

-0.51

iete

-0.48

CNP

-0.48

 Baillargeon

-0.48

ők

-0.48

といい

-0.47

POSITIVE LOGITS

us

4.14

Us

2.84

Us

2.33

 нас

1.93

 нами

1.89

 нам

1.88

 nous

1.77

us

1.71

 nosotros

1.70

me

1.69

Activations Density 0.045%

the word "us" in various contexts

No Comments

No Known Activations