INDEX

Explanations

terms related to the concept of 'unwanted' such as unwanted pregnancies, unwanted advances, or unwanted side effects

oai_token-act-pair · gpt-3.5-turbo

references to unwanted pregnancies and related issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hens

-0.91

alach

-0.87

olitan

-0.86

bard

-0.85

sis

-0.85

ophers

-0.84

etics

-0.84

sheets

-0.84

bleacher

-0.83

utra

-0.81

POSITIVE LOGITS

 pregnancies

1.06

 Parenthood

0.99

 pregnancy

0.92

 consequences

0.90

 unwanted

0.88

 consequence

0.86

 unintended

0.84

ãĤī

0.75

 surprises

0.74

 baggage

0.72

Activations Density 0.033%

terms related to the concept of 'unwanted' such as unwanted pregnancies, unwanted advances, or unwanted side effects

references to unwanted pregnancies and related issues

No Comments

No Known Activations