INDEX

Explanations

details related to specific physical locations

oai_token-act-pair · gpt-3.5-turbo

references to geographic locations

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

vous

-0.92

jin

-0.87

missions

-0.85

gres

-0.83

unes

-0.79

ights

-0.76

und

-0.73

tails

-0.73

haw

-0.70

tail

-0.70

POSITIVE LOGITS

 location

1.08

 locations

1.07

 locate

0.80

 Location

0.76

 Locations

0.70

finder

0.70

 locality

0.69

holder

0.69

 relocation

0.68

 localization

0.68

Activations Density 0.024%

details related to specific physical locations

references to geographic locations

No Comments

No Known Activations