INDEX

Explanations

words starting with the letter "P" with additional preference for words beginning with "Po", "Pon", "Pri", "Pre","Por", "Nap", or "Up".

oai_token-act-pair · gemini-2.0-flash

various programming and data format keywords

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

P

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

元

-0.44

 tight

-0.41

scha

-0.38

یه

-0.38

 auth

-0.38

vo

-0.36

||

-0.36

toLocale

-0.36

OD

-0.35

vol

-0.35

POSITIVE LOGITS

StructEnd

0.96

 FetchType

0.87

Демографія

0.82

Hentet

0.82

yntaxException

0.82

resave

0.81

:✨

0.78

GEBURTSDATUM

0.78

 الرياضيه

0.76

 المعيارى

0.76

Activations Density 0.386%

words starting with the letter "P" with additional preference for words beginning with "Po", "Pon", "Pri", "Pre","Por", "Nap", or "Up".

various programming and data format keywords

P

No Comments

No Known Activations