INDEX

Explanations

mentions of individuals being found deceased or harmed

oai_token-act-pair · gpt-3.5-turbo

instances of people being discovered in a deceased state

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

dayName

-0.83

yip

-0.83

lishes

-0.81

yright

-0.72

creation

-0.70

dos

-0.65

eatures

-0.65

rats

-0.64

 expectations

-0.64

annis

-0.63

POSITIVE LOGITS

 guilty

1.05

 Guilty

0.92

 dead

0.86

 tampering

0.78

âĸĪ

0.78

 unfit

0.74

 wanting

0.74

 lying

0.73

dylib

0.72

 liable

0.72

Activations Density 0.056%

mentions of individuals being found deceased or harmed

instances of people being discovered in a deceased state

No Comments

No Known Activations