INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Whenever

-0.07

ATL

-0.06

Whenever

-0.06

thresh

-0.06

 Evaluation

-0.06

 tests

-0.06

/sys

-0.06

Ibn

-0.06

 Question

-0.06

 educator

-0.06

POSITIVE LOGITS

работать

0.08

yme

0.07

 سم

0.07

 Eternal

0.07

僚

0.07

呜

0.07

setDescription

0.07

.optional

0.06

 FedEx

0.06

 synchronization

0.06

Activations Density 0.098%

No Comments

No Known Activations