INDEX

Explanations

technical terms related to programming frameworks and libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 propOrder

-0.72

endphp

-0.67

 مرئيه

-0.65

ToAction

-0.62

 Audiodateien

-0.60

})*/

-0.58

География

-0.58

 bParam

-0.55

ttemberg

-0.54

zęd

-0.51

POSITIVE LOGITS

Illuminate

2.16

ValueGenerated

1.26

rxjs

1.17

BeginContext

1.06

badlogic

0.91

reactivex

0.88

SpringBootTest

0.82

 hashCode

0.80

WireFormat

0.79

WriteTagHelper

0.79

Activations Density 0.009%

technical terms related to programming frameworks and libraries

No Comments

No Known Activations