INDEX

Explanations

words related to geopolitical locations, in particular the names of cities and provinces and in particular seeming to emphasize Argentina, France, and Iran

oai_token-act-pair · gemini-2.0-flash

tokens related to geographical locations or categories

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

places and regions

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

 EconPapers

-0.62

 futurs

-0.49

Numerology

-0.48

 transfieras

-0.47

itron

-0.46

 conférences

-0.46

 putus

-0.45

bein

-0.44

offrir

-0.44

 offert

-0.44

POSITIVE LOGITS

 disambiguazione

0.57

atista

0.57

󠁢

0.57

FlatList

0.54

useState

0.54

Referanser

0.53

achusetts

0.52

brainly

0.52

HtmlAttribute

0.51

Jai

0.51

Activations Density 2.385%

words related to geopolitical locations, in particular the names of cities and provinces and in particular seeming to emphasize Argentina, France, and Iran

tokens related to geographical locations or categories

places and regions

No Comments

No Known Activations