INDEX

Explanations

the word "que" 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 itſelf

-0.92

NameInMap

-0.86

 himſelf

-0.83

 myſelf

-0.82

 Reſ

-0.81

ſelf

-0.80

Eſ

-0.79

 Majefty

-0.79

 contextLoads

-0.79

 Beſ

-0.79

POSITIVE LOGITS

que

2.55

Que

2.20

Que

2.12

QUE

2.01

que

1.78

QUE

1.44

 què

1.21

 qué

1.13

Qué

1.08

che

1.01

Activations Density 0.012%

the word "que" in various contexts

No Comments

No Known Activations