INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 scaleFactor

-0.07

.sequence

-0.06

BET

-0.06

遄

-0.06

 benefit

-0.06

 confused

-0.06

stress

-0.06

壹

-0.06

beth

-0.06

dain

-0.06

POSITIVE LOGITS

acios

0.08

�

0.07

相继

0.07

宝安

0.07

 Bibli

0.07

-scripts

0.07

_admin

0.07

)."

0.07

How

0.07

Keyword

0.07

Activations Density 0.002%

No Comments

No Known Activations