INDEX

Explanations

geographical features and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

AutoresizingMask

-0.35

îtra

-0.34

calientes

-0.32

 فريبيس

-0.32

DropTable

-0.31

 brush

-0.30

resizingMask

-0.30

 introdu

-0.30

ex

-0.30

Spoljašnje

-0.30

POSITIVE LOGITS

 Beach

1.00

Beach

0.98

 beach

0.94

beach

0.92

 BEACH

0.89

 beaches

0.87

 seashore

0.87

 beachfront

0.86

 Seaside

0.84

 seaside

0.82

Activations Density 0.624%

geographical features and locations

No Comments

No Known Activations