INDEX

Explanations

specific product names and their associated features or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 Kirkpatrick

-0.39

 Myers

-0.38

 Harlow

-0.37

 Hodges

-0.35

 Zapata

-0.34

 Jane

-0.34

 Osborne

-0.34

 Sorensen

-0.34

ips

-0.34

 Tierney

-0.32

POSITIVE LOGITS

 Galaxy

1.00

Galaxy

0.95

 Samsung

0.90

Samsung

0.85

 galaxy

0.82

 samsung

0.82

 SAMSUNG

0.81

galaxy

0.80

 سامسونگ

0.77

三星

0.74

Activations Density 0.205%

specific product names and their associated features or specifications

No Comments

No Known Activations