INDEX

Explanations

numbers in the context of dates and publication years

oai_token-act-pair · gpt-3.5-turbo

phrases indicating specific dates, locations, and contextual framing in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

iatrics

-0.85

rio

-0.83

endered

-0.77

ellar

-0.74

orsi

-0.74

bush

-0.73

gen

-0.72

ernal

-0.71

hovah

-0.70

icter

-0.69

POSITIVE LOGITS

 Provided

0.83

 Influ

0.70

 Sketch

0.66

 guiActiveUnfocused

0.64

TED

0.63

 airs

0.62

Ded

0.62

actionDate

0.60

 Travels

0.60

 Creed

0.60

Activations Density 0.317%

numbers in the context of dates and publication years

phrases indicating specific dates, locations, and contextual framing in text

No Comments

No Known Activations