INDEX

Explanations

a variety of common words and punctuation, often appearing in long compound sentences

oai_token-act-pair · gemini-2.0-flash

the word "for"

np_token-act-pair-logits · gpt-4o-mini

comma

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

homonymie

-0.65

曖昧さ回避

-0.63

DataAnnotations

-0.59

[]:

-0.55

Lähteet

-0.54

AndEndTag

-0.53

脚注の使い方

-0.52

তথ্যসূত্র

-0.52

Referanser

-0.50

 Потому

-0.50

POSITIVE LOGITS

for

2.67

for

1.87

 для

1.54

 für

1.46

 voor

1.45

FOR

1.44

For

1.41

 untuk

1.39

For

1.38

 για

1.30

Activations Density 3.746%

a variety of common words and punctuation, often appearing in long compound sentences

the word "for"

comma

No Comments

No Known Activations

a variety of common words and punctuation, often appearing in long compound sentences

the word "for"

comma

No Comments

No Known Activations