INDEX

Explanations

conditional words or phrases like "if", "when", and "but"

oai_token-act-pair · gemini-2.0-flash

conditionals

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Normdatei

-0.79

<bos>

-0.75

 when

-0.75

 Савезне

-0.73

if

-0.70

 because

-0.69

 autorytatywna

-0.68

MLLoader

-0.67

 while

-0.65

ValueStyle

-0.64

POSITIVE LOGITS

 Якщо

0.64

 When

0.64

When

0.62

If

0.60

For

0.60

As

0.59

With

0.58

 With

0.56

Since

0.56

 Если

0.56

Activations Density 2.549%

conditional words or phrases like "if", "when", and "but"

conditionals

No Comments

No Known Activations