INDEX

Explanations

personal accounts of experiences at malls and other public places

oai_token-act-pair · gemini-2.0-flash

Describing experiences

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

原始内容存档于

-0.59

niająca

-0.55

 ویکی‌پدیای

-0.54

urgery

-0.52

 säll

-0.52

PROMOTED

-0.51

#+#

-0.50

 consultato

-0.50

 XCTest

-0.50

 radiology

-0.50

POSITIVE LOGITS

StructEnd

0.54

 referenties

0.52

 estekak

0.52

 Sett

0.50

 settled

0.50

 Normdatei

0.50

setVerticalGroup

0.46

sette

0.46

 headed

0.46

PerformLayout

0.46

Activations Density 1.431%

personal accounts of experiences at malls and other public places

Describing experiences

No Comments

No Known Activations