INDEX

Explanations

locations and related identifiers within text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Prepositions "in" and "from" followed by a location

np_acts-logits-general · gemini-2.0-flash

places after 'in'

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Дон

-0.47

enumi

-0.43

 rég

-0.42

 hier

-0.42

九州

-0.41

iffe

-0.41

 Maharashtra

-0.41

tó

-0.41

rsiniz

-0.41

 biografi

-0.40

POSITIVE LOGITS

 Wikimedijinoj

0.69

expandindo

0.66

 kala

0.65

 Nobles

0.64

 Audiodateien

0.63

Osh

0.63

Puy

0.62

 estekak

0.61

 Mank

0.61

awaiter

0.60

Activations Density 0.400%

locations and related identifiers within text

Prepositions "in" and "from" followed by a location

places after 'in'

No Comments

No Known Activations