INDEX

Explanations

phrases related to caution, prevention, or maintenance

oai_token-act-pair · gpt-3.5-turbo

negations and phrases indicating avoidance or prevention

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Options

-0.67

isSpecialOrderable

-0.66

Newsletter

-0.64

 largeDownload

-0.64

 congratulations

-0.63

 Houses

-0.61

 Kinnikuman

-0.60

 Cors

-0.60

 Newsp

-0.60

YES

-0.59

POSITIVE LOGITS

 accidentally

1.04

 inadvertently

1.04

 interfere

1.01

 disturb

1.01

 jeopard

1.01

 undue

0.98

 unnecessarily

0.97

 ruin

0.96

 contam

0.95

 unintentionally

0.95

Activations Density 0.255%

phrases related to caution, prevention, or maintenance

negations and phrases indicating avoidance or prevention

No Known Activations