INDEX

Explanations

references to the word "Dou"

oai_token-act-pair · gpt-3.5-turbo

references to the Douro River and its significance

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

ocene

-0.92

 guiActiveUnfocused

-0.86

IST

-0.85

opathy

-0.76

 Equip

-0.73

akeru

-0.70

Downloadha

-0.69

OHN

-0.67

ocamp

-0.66

 Occupations

-0.65

POSITIVE LOGITS

bled

1.35

bles

1.31

bling

1.30

plet

1.08

blers

1.06

bler

1.03

bt

1.02

pler

0.94

plets

0.94

ble

0.93

Activations Density 0.015%

references to the word "Dou"

references to the Douro River and its significance

No Comments

No Known Activations