INDEX

Explanations

words related to traditional or old-fashioned practices or objects

oai_token-act-pair · gpt-3.5-turbo

words associated with traditional or classic styles

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

ese

-0.83

esville

-0.81

urrent

-0.76

worthiness

-0.73

hip

-0.71

anon

-0.71

board

-0.69

itor

-0.69

ity

-0.68

ysis

-0.67

POSITIVE LOGITS

 srfAttach

0.74

Īè

0.71

 adolesc

0.71

 conflic

0.70

Ð»

0.69

Ī

0.69

 disadvant

0.69

ĸļ

0.69

chin

0.65

eners

0.65

Activations Density 0.045%

words related to traditional or old-fashioned practices or objects

words associated with traditional or classic styles

No Comments

No Known Activations