INDEX

Explanations

words related to professions, particularly ending in '-ician'

oai_token-act-pair · gpt-3.5-turbo

words related to professionals in the medical and healthcare fields

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

McC

-0.73

Jake

-0.70

 McGregor

-0.65

 Merrill

-0.65

Ev

-0.65

 Predator

-0.64

imm

-0.63

 Predators

-0.63

æĢ

-0.62

Blake

-0.62

POSITIVE LOGITS

icians

1.44

ician

1.36

anguage

0.97

utical

0.94

soever

0.93

ftime

0.92

lectic

0.88

nown

0.88

naire

0.81

uador

0.81

Activations Density 0.012%

words related to professions, particularly ending in '-ician'

words related to professionals in the medical and healthcare fields

No Comments

No Known Activations