INDEX

Explanations

technical jargon and acronyms related to programming or database contexts

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

cvtColor

-0.63

 HomeComponent

-0.62

GetKeyDown

-0.61

landır

-0.59

AspNet

-0.54

 AppBundle

-0.53

culoskeletal

-0.52

IsPostBack

-0.52

]])

-0.52

}))

-0.52

POSITIVE LOGITS

TPS

0.94

 Townsend

0.93

Taz

0.92

 Tully

0.86

TMC

0.86

TLR

0.86

QMetaType

0.85

 Tavares

0.85

 Tavern

0.85

Tt

0.85

Activations Density 1.885%

technical jargon and acronyms related to programming or database contexts

No Comments

No Known Activations