INDEX

Explanations

sentences that describe trends

oai_token-act-pair · gemini-2.0-flash

a/an

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

WireFormatLite

-0.66

LookAnd

-0.62

 Réponses

-0.60

RuleContext

-0.55

 cous

-0.54

mbol

-0.54

mbols

-0.54

Alike

-0.54

 Dall

-0.53

ịa

-0.52

POSITIVE LOGITS

GEBURTSDATUM

0.50

 argint

0.50

DispatchToProps

0.48

 rechange

0.47

genomen

0.47

 démocr

0.46

 tromper

0.46

 dommages

0.44

 choisissez

0.44

arama

0.44

Activations Density 1.133%

sentences that describe trends

a/an

No Comments

No Known Activations