INDEX

Explanations

mentions related to the topic of abortion

oai_token-act-pair · gpt-3.5-turbo

terms related to abortion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Tang

-0.69

Wak

-0.68

raq

-0.67

 Lion

-0.67

 Powered

-0.66

 Ding

-0.65

rit

-0.65

Dai

-0.64

 Seas

-0.64

 Ming

-0.64

POSITIVE LOGITS

 abortion

3.67

 Abortion

3.17

 abortions

3.01

abortion

2.62

 contraception

1.75

 contraceptive

1.74

 Parenthood

1.66

 miscarriage

1.66

 contraceptives

1.65

 Planned

1.61

Activations Density 0.027%

mentions related to the topic of abortion

terms related to abortion

No Comments

No Known Activations