INDEX

Explanations

apologies or statements of regret

oai_token-act-pair · gpt-3.5-turbo

expressions of apology and regret

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

FTWARE

-0.79

DragonMagazine

-0.78

bard

-0.75

kefeller

-0.73

fman

-0.69

atown

-0.67

vantage

-0.67

otic

-0.66

Ready

-0.64

 Mehran

-0.64

POSITIVE LOGITS

 mistakes

1.25

 inconvenience

1.16

 inconven

1.14

mist

1.05

 hurting

1.03

 unintentional

1.02

 unintentionally

1.01

 offended

1.00

 ruining

1.00

 sins

1.00

Activations Density 0.145%

apologies or statements of regret

expressions of apology and regret

No Known Activations