INDEX

Explanations

javascript code snippets related to tweets

oai_token-act-pair · gemini-2.0-flash

tweets

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

 HasFactory

-0.86

+#+#

-0.85

 незавершена

-0.77

 lenker

-0.73

 متعلقه

-0.67

 Jefus

-0.67

 AspNetCore

-0.65

UnusedPrivate

-0.65

хьтан

-0.65

цезда

-0.60

POSITIVE LOGITS

 tweet

1.24

 tweeted

1.20

 tweets

1.15

 tweeting

1.10

 Tweet

1.05

 Tweets

1.03

 Twitter

0.98

 twit

0.94

Tweet

0.93

tweet

0.92

Activations Density 1.191%

javascript code snippets related to tweets

tweets

No Comments

No Known Activations