INDEX

Explanations

references to refugee-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to refugees and the refugee crisis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abeth

-0.85

phalt

-0.81

paio

-0.80

aple

-0.76

ĪĴ

-0.76

cor

-0.75

 Rove

-0.74

estial

-0.74

auga

-0.73

apeake

-0.73

POSITIVE LOGITS

 refugee

1.30

 resettlement

1.30

 refugees

1.23

 Refugee

1.20

 Refugees

1.16

 asylum

1.01

 camps

0.98

 Relief

0.93

 relief

0.91

 shelters

0.90

Activations Density 0.017%

references to refugee-related terms

terms related to refugees and the refugee crisis

No Comments

No Known Activations