INDEX

Explanations

geographical locations, particularly bodies of water and rivers

oai_token-act-pair · gpt-3.5-turbo

geographical locations and rivers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

mates

-0.81

thood

-0.80

CHQ

-0.77

aspers

-0.76

 diapers

-0.73

 copies

-0.69

byter

-0.68

 attendance

-0.68

 audiences

-0.68

DJs

-0.67

POSITIVE LOGITS

 Mountains

1.49

 River

1.38

 river

1.36

 coastline

1.35

 basin

1.31

 peninsula

1.28

 footh

1.27

 Basin

1.22

 ridge

1.22

 mountains

1.21

Activations Density 0.292%

geographical locations, particularly bodies of water and rivers

geographical locations and rivers

No Comments

No Known Activations