INDEX

Explanations

references to dates and temporal phrases

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

dates in the format Month Year

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 abound

-0.65

plays

-0.64

withstanding

-0.63

 acronym

-0.61

 grit

-0.59

 filament

-0.59

anchester

-0.59

 mustache

-0.57

 withstand

-0.57

 toast

-0.56

POSITIVE LOGITS

 Notting

0.80

cember

0.79

DragonMagazine

0.75

 onwards

0.75

imester

0.75

stice

0.74

 Maiden

0.73

displayText

0.72

 Sands

0.69

oway

0.68

Activations Density 0.364%

references to dates and temporal phrases

dates in the format Month Year

No Comments

No Known Activations