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

NFC

-0.06

شن

-0.06

焦点

-0.06

ccione

-0.06

eec

-0.06

 sund

-0.06

.OrdinalIgnoreCase

-0.06

ibo

-0.06

 organise

-0.06

=true

-0.06

POSITIVE LOGITS

 Compute

0.07

 glove

0.07

 Ultimately

0.07

 glVertex

0.07

Skipping

0.07

Segment

0.07

 Thể

0.06

 Determin

0.06

 attacker

0.06

 )↵↵↵

0.06

Activations Density 0.039%

No Comments

No Known Activations