INDEX

Explanations

articles that are using the words the, is, to, a, in, and my. Focusing on common word usage within the article

oai_token-act-pair · gemini-2.0-flash

Formal writing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

for

-1.02

not

-1.02

the

-1.02

part

-1.00

first

-1.00

time

-0.99

form

-0.97

set

-0.96

right

-0.96

one

-0.96

POSITIVE LOGITS

marginHorizontal

0.48

reloadData

0.42

sstream

0.41

wantErr

0.41

marginVertical

0.40

alignSelf

0.40

setViewport

0.39

flexDirection

0.39

beforeSend

0.38

onCancel

0.38

Activations Density 38.987%

articles that are using the words the, is, to, a, in, and my. Focusing on common word usage within the article

Formal writing

No Comments

No Known Activations