INDEX

Explanations

words and phrases where the author makes a recommendation to the reader, urging them to take some particular action.

oai_token-act-pair · gemini-2.0-flash

patterns starting with 'you' followed by verbs or commands

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

action encouragement

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

DockStyle

-1.03

 المعيارى

-1.03

expandindo

-0.98

WriteTagHelper

-0.94

Efq

-0.91

 unknownFields

-0.87

Eſ

-0.87

 whoſe

-0.86

 ویکی‌آمباردا

-0.85

 becauſe

-0.84

POSITIVE LOGITS

 head

0.50

per

0.49

del

0.39

pl

0.38

fon

0.38

uc

0.37

pu

0.37

<eos>

0.36

冲

0.36

Activations Density 0.890%

words and phrases where the author makes a recommendation to the reader, urging them to take some particular action.

patterns starting with 'you' followed by verbs or commands

action encouragement

No Comments

No Known Activations