INDEX

Explanations

occurrences of the term "associate."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Personensuche

-0.64

 collected

-0.58

 "..\..\..\

-0.57

 vole

-0.56

 headed

-0.55

воло

-0.54

principalColumn

-0.52

GOTREF

-0.52

drawString

-0.50

 subsequent

-0.50

POSITIVE LOGITS

 Associate

1.18

Associate

1.08

associate

1.07

 associate

1.07

 associates

1.00

 Associates

0.97

 affiliate

0.92

Associ

0.90

associ

0.87

 ASSOCIATES

0.81

Activations Density 0.071%

occurrences of the term "associate."

No Comments

No Known Activations