INDEX

Explanations

words related to statistics and geographical locations, especially in Europe

oai_token-act-pair · gemini-2.0-flash

foreign language terms or phrases

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

Architecture and real estate

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

CloseOperation

-0.71

WithIOException

-0.70

uxxxx

-0.69

ագրություններ

-0.68

脚注の使い方

-0.66

ChildScrollView

-0.63

 defaultstate

-0.60

IntentFilter

-0.59

tvguidetime

-0.57

PRNewswire

-0.57

POSITIVE LOGITS

quité

0.49

förmig

0.47

 volna

0.47

 chóng

0.47

 biệt

0.45

izaje

0.45

hoedd

0.44

 studio

0.44

 Armored

0.44

 étu

0.44

Activations Density 0.575%

words related to statistics and geographical locations, especially in Europe

foreign language terms or phrases

Architecture and real estate

No Comments

No Known Activations