INDEX

Explanations

proper nouns related to the city of Baltimore

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Baltimore" and its related terms

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

yip

-1.05

uador

-0.89

mble

-0.85

utterstock

-0.80

yss

-0.77

pter

-0.76

aeda

-0.76

wagen

-0.75

aterasu

-0.74

rencies

-0.74

POSITIVE LOGITS

 Orioles

1.20

 Ravens

1.01

 Colts

0.90

 Wire

0.87

 City

0.87

 County

0.85

 Hopkins

0.81

 Citiz

0.79

 Harbor

0.79

 Yards

0.79

Activations Density 0.011%

proper nouns related to the city of Baltimore

occurrences of the word "Baltimore" and its related terms

No Comments

No Known Activations