INDEX

Explanations

references to specific periods of time, especially decades

oai_token-act-pair · gpt-3.5-turbo

references to specific decades and their associated cultural or historical events

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

Magikarp

-0.66

 continu

-0.64

 categ

-0.60

 stret

-0.60

wat

-0.58

 congr

-0.58

Fram

-0.58

 Polic

-0.56

 Cant

-0.56

 propriet

-0.55

POSITIVE LOGITS

ixties

1.03

-'

0.87

ties

0.83

inian

0.82

enium

0.80

 onwards

0.74

yip

0.74

iatus

0.70

ounters

0.70

lins

0.70

Activations Density 0.064%

references to specific periods of time, especially decades

references to specific decades and their associated cultural or historical events

No Comments

No Known Activations