INDEX

Explanations

academic papers mentioning seasonal changes and hypothesis testing

oai_token-act-pair · gemini-2.0-flash

prediction

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

 članak

-0.52

telse

-0.50

ocities

-0.50

 BorderRadius

-0.49

jgl

-0.49

protoc

-0.48

 snippetHide

-0.47

 surla

-0.46

참고

-0.45

ButtonItem

-0.43

POSITIVE LOGITS

 prediction

0.68

 predictions

0.67

 Predictions

0.67

 predicts

0.66

 predict

0.65

 Prediction

0.65

fromnode

0.63

 predicted

0.63

Prediction

0.60

Predictions

0.60

Activations Density 8.244%

academic papers mentioning seasonal changes and hypothesis testing

prediction

No Comments

No Known Activations