INDEX

Explanations

mentions of the country "Norway"

oai_token-act-pair · gpt-3.5-turbo

mentions of Norway and its derivatives

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

ual

-0.80

place

-0.79

uers

-0.78

aging

-0.77

ually

-0.77

ept

-0.75

plain

-0.74

xxxxxxxx

-0.73

uring

-0.71

enance

-0.70

POSITIVE LOGITS

Bok

1.03

borg

0.95

 Norway

0.93

wegian

0.92

 Refugee

0.91

 Norwegian

0.85

 Oslo

0.84

 Airlines

0.81

Dag

0.78

Ń·

0.75

Activations Density 0.016%

mentions of the country "Norway"

mentions of Norway and its derivatives

No Comments

No Known Activations