INDEX

Explanations

imperative statements or recommendations, often including "you" and "should"

oai_token-act-pair · gemini-2.0-flash

give

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

XmlAccessType

-0.73

 فريبيس

-0.71

Personendaten

-0.58

 doInBackground

-0.57

 FontWeight

-0.55

aarrggbb

-0.54

UrlResolution

-0.50

 lenker

-0.50

 <>",

-0.50

ArgsConstructor

-0.49

POSITIVE LOGITS

 give

2.36

Give

2.34

 Give

2.34

give

2.31

 giving

2.14

 GIVE

1.99

 Giving

1.99

giving

1.95

Giving

1.95

 gave

1.94

Activations Density 3.088%

imperative statements or recommendations, often including "you" and "should"

give

No Comments

No Known Activations