INDEX

Explanations

references to geographic locations and associated details

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

Punctuation within addresses/locations

np_acts-logits-general · gemini-2.0-flash

addresses and specific locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

уза

-0.49

 tanto

-0.46

chieben

-0.46

ellschaft

-0.45

 percent

-0.43

 because

-0.43

da

-0.43

piecze

-0.42

ос

-0.42

orological

-0.41

POSITIVE LOGITS

Efq

0.77

 Cedex

0.75

〒

0.73

GEBURTSDATUM

0.71

 Tél

0.71

الإنجليزية

0.70

poptosis

0.70

 postcode

0.69

RegistryLite

0.67

 Telephone

0.66

Activations Density 0.140%

references to geographic locations and associated details

Punctuation within addresses/locations

addresses and specific locations

No Comments

No Known Activations