INDEX

Explanations

words indicating the temporal context for some action

oai_token-act-pair · gemini-2.0-flash

start, beginning

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ględ

-0.58

 vicente

-0.52

Бележки

-0.46

XMLSchema

-0.43

ongeza

-0.42

ługość

-0.42

avras

-0.41

 shallow

-0.40

anstalt

-0.40

potranspiration

-0.40

POSITIVE LOGITS

HostException

0.71

GOTREF

0.71

enumii

0.66

RectangleBorder

0.66

 resourceCulture

0.66

 tartalomajánló

0.64

ReusableCell

0.59

 redan

0.59

depuis

0.58

ंदीखरीदारी

0.57

Activations Density 1.428%

words indicating the temporal context for some action

start, beginning

No Comments

No Known Activations