INDEX

Explanations

the use of words 'is', 'are', 'then','were', 'being' and other forms of the verb 'to be'

oai_token-act-pair · gemini-2.0-flash

data analysis and comparisons

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ագրություններ

-0.88

出版年

-0.74

 onCancelled

-0.67

发表于

-0.64

mybatisplus

-0.63

DockStyle

-0.63

المناصب

-0.62

withIdentifier

-0.61

!*\

-0.61

ьа

-0.61

POSITIVE LOGITS

🍣

0.47

 Grocery

0.45

0.42

 puts

0.41

rè

0.41

 reflexes

0.40

Put

0.40

 arada

0.40

ometer

0.39

 maroca

0.39

Activations Density 5.915%

the use of words 'is', 'are', 'then','were', 'being' and other forms of the verb 'to be'

data analysis and comparisons

No Comments

No Known Activations