INDEX

Explanations

specific geographic locations and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Soria

-0.67

/**

-0.66

">//

-0.59

 otomatig

-0.58

 "..\..\..\

-0.58

 Pogba

-0.56

alsy

-0.55

 Altitude

-0.54

 cyanide

-0.54

 AspNetCore

-0.53

POSITIVE LOGITS

 coastal

1.33

 beach

1.22

 Coastal

1.18

Coastal

1.18

 beaches

1.14

coastal

1.12

 Beach

1.09

beach

1.08

coast

1.07

 BEACH

1.05

Activations Density 1.675%

specific geographic locations and related terms

No Comments

No Known Activations