INDEX

Explanations

statements that express future intentions or predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

存于互联网档案馆

-1.01

Composable

-0.97

GEBURTSDATUM

-0.83

 contextLoads

-0.78

 <<<<<<<<<<<<<<

-0.77

parsedMessage

-0.76

 Krakowie

-0.75

 Comer

-0.74

 newData

-0.73

-------

-0.72

POSITIVE LOGITS

 WILL

1.29

 will

1.27

 Will

1.14

WILL

1.09

be

1.02

will

0.96

Will

0.93

 would

0.89

can

0.88

 likely

0.86

Activations Density 0.174%

statements that express future intentions or predictions

No Comments

No Known Activations