INDEX

Explanations

state

np_max-act · gemini-2.0-flash

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

 nunca

-0.07

Tv

-0.07

 criticisms

-0.07

 filmes

-0.07

IOException

-0.06

这么

-0.06

 resto

-0.06

 Manga

-0.06

$core

-0.06

Bs

-0.06

POSITIVE LOGITS

 door

0.07

uil

0.06

ใส

0.06

AMP

0.06

CTL

0.06

DL

0.06

drop

0.06

 ********************************************************

0.06

ער

0.06

 ############

0.06

Activations Density 0.002%

state

No Comments

No Known Activations