INDEX

Explanations

words and short phrases used in multiple computer languages, especially those indicating logic

oai_token-act-pair · gemini-2.0-flash

Non-English code/language

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 BorderRadius

-0.70

㎡

-0.68

jectures

-0.68

 tslint

-0.67

Rgds

-0.65

addContainerGap

-0.64

ſure

-0.64

AnchorStyles

-0.63

onaut

-0.63

édrale

-0.63

POSITIVE LOGITS

 because

1.54

because

1.45

Because

1.45

 Because

1.36

<bos>

1.34

 BECAUSE

1.20

 porque

1.10

因为

1.09

 since

1.06

 omdat

1.02

Activations Density 0.990%

words and short phrases used in multiple computer languages, especially those indicating logic

Non-English code/language

No Comments

No Known Activations