INDEX

Explanations

specific references to historical locations or landmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Urugu

-0.71

 schwed

-0.60

 Finnish

-0.59

ContentAsync

-0.57

 Swedish

-0.56

Finnish

-0.56

 Davao

-0.52

 архивлан

-0.51

 Sweden

-0.51

 finland

-0.51

POSITIVE LOGITS

 Virginia

1.64

Virginia

1.50

 VIRGINIA

1.35

 virginia

1.25

 Charlottesville

1.21

 Richmond

1.18

 Roanoke

1.17

UVA

1.16

 Shenandoah

1.09

Va

1.09

Activations Density 0.210%

specific references to historical locations or landmarks

No Comments

No Known Activations