INDEX

Explanations

references to the country Brazil

oai_token-act-pair · gpt-3.5-turbo

occurrences of the country "Brazil."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

********************************

-0.77

################################

-0.72

LEASE

-0.70

dfx

-0.68

################

-0.66

asonable

-0.64

creen

-0.63

enting

-0.62

ancies

-0.62

DH

-0.61

POSITIVE LOGITS

Jiu

1.08

 Paulo

1.02

inho

0.93

 Brazil

0.93

Ã£o

0.91

 Janeiro

0.91

 Portuguese

0.87

ians

0.85

orius

0.84

Brazil

0.82

Activations Density 0.007%

references to the country Brazil

occurrences of the country "Brazil."

No Comments

No Known Activations