INDEX

Explanations

mentions of the term "abortion."

oai_token-act-pair · gpt-3.5-turbo

terms related to abortion and its regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Flavoring

-1.05

âĵĺ

-0.87

hew

-0.83

Else

-0.75

 guiActiveUnfocused

-0.70

Rail

-0.69

Rew

-0.69

)=(

-0.69

SAM

-0.68

Ear

-0.67

POSITIVE LOGITS

 abortion

1.06

 abortions

0.99

abortion

0.86

 contraceptive

0.85

 termination

0.81

 clinics

0.80

 contraception

0.80

 Parenthood

0.80

 pills

0.79

sex

0.79

Activations Density 0.016%

mentions of the term "abortion."

terms related to abortion and its regulations

No Comments

No Known Activations