INDEX

Explanations

phrases that discuss abstract ideas and concepts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 bakgrund

-0.61

 سكانية

-0.56

انتهای

-0.54

 Leurs

-0.51

 propOrder

-0.51

 Iden

-0.50

 vanskelig

-0.48

 confiance

-0.48

 accordingly

-0.48

strat

-0.47

POSITIVE LOGITS

 notion

0.73

DrawerToggle

0.71

 concept

0.69

ceptre

0.67

bcryptjs

0.67

SeekBar

0.67

attere

0.65

HasForeignKey

0.65

reactstrap

0.63

setViewportView

0.63

Activations Density 0.319%

phrases that discuss abstract ideas and concepts

No Known Activations