INDEX

Explanations

terms related to urban environments

oai_token-act-pair · gpt-3.5-turbo

mentions of urban topics or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

xon

-0.91

cius

-0.80

 Canaver

-0.79

etsk

-0.79

othal

-0.79

yip

-0.76

terday

-0.75

utics

-0.74

hemy

-0.74

arez

-0.69

POSITIVE LOGITS

ization

1.24

ized

1.13

izing

1.05

isation

1.00

izations

0.95

ities

0.94

scape

0.94

icity

0.93

 dwell

0.93

 renewal

0.93

Activations Density 0.040%

terms related to urban environments

mentions of urban topics or concepts

No Comments

No Known Activations