INDEX

Explanations

references to architects and architectural achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.89

 propOrder

-0.80

 SqlCommand

-0.68

CastException

-0.65

TypedDataSet

-0.63

VideoCapture

-0.63

 مشين

-0.63

ActivityCompat

-0.62

XmlAccessType

-0.62

 utafitiHapana

-0.61

POSITIVE LOGITS

 design

1.11

 architects

1.07

 architect

1.05

 designers

1.03

 designs

0.98

 designer

0.96

 architectural

0.96

 Design

0.95

 Architects

0.93

 Designers

0.91

Activations Density 0.134%

references to architects and architectural achievements

No Comments

No Known Activations