INDEX

Explanations

phrases related to a specific geographical location, specifically "West"

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "West"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etsk

-0.95

staking

-0.94

 confir

-0.93

veyard

-0.90

displayText

-0.88

channelAvailability

-0.86

cffff

-0.85

aminer

-0.83

Downloadha

-0.83

 reluct

-0.82

POSITIVE LOGITS

 Indies

1.18

 Coast

1.07

lake

1.03

side

1.02

minster

1.02

cott

0.98

bury

0.97

 Wing

0.96

phal

0.96

 Midlands

0.95

Activations Density 0.021%

phrases related to a specific geographical location, specifically "West"

mentions of the term "West"

No Comments

No Known Activations