INDEX

Explanations

lobes or words containing "lobe"

oai_token-act-pair · gpt-3.5-turbo

references to lobes and lobotomies in medical contexts

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

 Marketable

-0.94

externalActionCode

-0.89

Constructed

-0.87

Male

-0.85

Downloadha

-0.80

 Serious

-0.79

é¾įå¥ĳå£«

-0.77

++++

-0.76

Female

-0.75

 Ethnic

-0.74

POSITIVE LOGITS

otom

1.52

lob

1.47

otomy

1.33

emouth

1.17

acies

1.12

etooth

1.09

bing

0.98

tailed

0.97

bage

0.92

rosc

0.89

Activations Density 0.005%

lobes or words containing "lobe"

references to lobes and lobotomies in medical contexts

No Comments

No Known Activations