INDEX

Explanations

locations, specifically cities

oai_token-act-pair · gpt-3.5-turbo

mentions of specific locations or city names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ramid

-1.02

awaru

-0.88

aceous

-0.82

rolog

-0.80

-0.77

acea

-0.77

ascript

-0.76

igm

-0.74

abet

-0.73

vana

-0.72

POSITIVE LOGITS

 Newark

0.94

shire

0.92

 skyline

0.82

 Harbor

0.76

 Baptist

0.76

 Airport

0.76

mong

0.72

 Downtown

0.72

 Marriott

0.71

 Chinatown

0.70

Activations Density 0.015%

locations, specifically cities

mentions of specific locations or city names

No Comments

No Known Activations