INDEX

Explanations

references to caps or cap structures in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

Referències

-0.81

"/></

-0.68

 imageName

-0.66

."<

-0.66

='')

-0.64

]<<"

-0.64

}*/

-0.63

//.

-0.63

 Granger

-0.63

."</

-0.61

POSITIVE LOGITS

cap

2.53

Cap

2.51

Cap

2.50

cap

2.35

 caps

2.32

 Caps

2.16

CAP

2.00

caps

1.85

CAP

1.83

Caps

1.80

Activations Density 0.064%

references to caps or cap structures in scientific or technical contexts

No Comments

No Known Activations