INDEX

Explanations

references to the location "Dunedin."

oai_token-act-pair · gpt-3.5-turbo

references to the name "Dun."

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

OHN

-0.78

NRS

-0.71

xual

-0.65

âĸĪâĸĪ

-0.64

Magikarp

-0.63

INT

-0.61

>>>>>>>>

-0.61

ONS

-0.61

shapeshifter

-0.60

 Pyro

-0.59

POSITIVE LOGITS

edin

1.03

wich

1.01

querque

1.00

leys

0.94

lap

0.92

igan

0.89

ogh

0.89

iet

0.87

agon

0.85

omial

0.85

Activations Density 0.013%

references to the location "Dunedin."

references to the name "Dun."

No Comments

No Known Activations