INDEX

Explanations

terms related to inheritance and succession

oai_token-act-pair · gpt-3.5-turbo

terms related to inheritance and lineage

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

the word 'heir'

oai_token-act-pair · gpt-4-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Esp

-0.73

 Staff

-0.72

 Baird

-0.69

 Canad

-0.66

humane

-0.66

 Oval

-0.65

 Packers

-0.65

 Airl

-0.63

 Lange

-0.62

 Leather

-0.61

POSITIVE LOGITS

 heir

1.20

 heirs

1.17

 inher

0.90

archy

0.83

ãĤ¼ãĤ¦ãĤ¹

0.80

 challeng

0.79

idious

0.78

 execut

0.76

unia

0.75

mares

0.74

Activations Density 0.007%

terms related to inheritance and succession

terms related to inheritance and lineage

the word 'heir'

No Comments

No Known Activations