INDEX

Explanations

references to locations or features in geographic or urban contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

fromLTRB

-0.42

SharedDtor

-0.38

centralwidget

-0.38

AndEndTag

-0.35

VL

-0.34

alibaba

-0.33

lwjgl

-0.33

 resultCode

-0.32

 dataSnapshot

-0.32

AxisAlignment

-0.32

POSITIVE LOGITS

 Bermuda

0.73

 Cayman

0.67

Bermuda

0.65

 disambiguazione

0.59

 bermuda

0.59

bermuda

0.57

Билгалдахарш

0.53

 CanadaChoose

0.52

 perlas

0.48

 kaarangay

0.48

Activations Density 0.066%

references to locations or features in geographic or urban contexts

No Comments

No Known Activations