INDEX

Explanations

references to operating systems, specifically iOS and macOS

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Enders

-0.79

 Michel

-0.61

 Sampson

-0.61

 Jeffries

-0.60

 Washburn

-0.60

 pane

-0.58

Michel

-0.58

 Pemberton

-0.58

 Luxembourg

-0.57

 Andi

-0.57

POSITIVE LOGITS

iOS

1.52

iOS

1.42

IOS

1.21

ios

1.20

ios

1.20

IOS

1.05

 Firmware

0.92

+#+#

0.88

 firmware

0.87

/***/

0.86

Activations Density 0.096%

references to operating systems, specifically iOS and macOS

No Comments

No Known Activations