INDEX

Explanations

references to significant documents or publications, especially in academic or legal contexts

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

Location after preposition "in"

np_acts-logits-general · gemini-2.0-flash

city names

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

genstein

-0.56

 Mennon

-0.55

 calore

-0.53

 Algerian

-0.51

 Etrus

-0.50

öffnet

-0.49

 Belarusian

-0.48

 Erit

-0.48

 Taliban

-0.48

 Plaid

-0.47

POSITIVE LOGITS

 London

1.39

London

1.19

 Paris

1.09

 Chicago

1.09

 Toronto

1.09

 Washington

1.07

 Tokyo

1.03

 Madrid

1.02

 Philadelphia

1.00

 Londres

1.00

Activations Density 0.406%

references to significant documents or publications, especially in academic or legal contexts

Location after preposition "in"

city names

No Comments

No Known Activations