INDEX

Explanations

locations within Dublin

oai_token-act-pair · gpt-3.5-turbo

references to the city of Dublin and its associated entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ļéĨĴ

-0.73

oted

-0.72

olars

-0.71

aturdays

-0.71

kaya

-0.70

imov

-0.69

anooga

-0.68

alus

-0.68

 autop

-0.68

ļé

-0.67

POSITIVE LOGITS

 Gael

0.91

 Duffy

0.83

 Cork

0.76

 Byrne

0.75

 McCann

0.74

patrick

0.73

 Ireland

0.72

forth

0.72

mares

0.72

Ireland

0.70

Activations Density 0.087%

locations within Dublin

references to the city of Dublin and its associated entities

No Comments

No Known Activations