INDEX

Explanations

words related to hormones and neurotransmitters

oai_token-act-pair · gpt-3.5-turbo

terms related to hormones and their effects on behavior and health

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

Negative Logits

GAN

-0.84

EMS

-0.78

 Sect

-0.75

 Shant

-0.75

cook

-0.72

 Hallow

-0.71

 Parish

-0.69

 Hosp

-0.68

 Weaver

-0.68

 Cloud

-0.68

POSITIVE LOGITS

 testosterone

3.42

osterone

2.15

 masculinity

1.94

 dopamine

1.86

 cortisol

1.85

 mascul

1.64

 estrogen

1.64

 serotonin

1.59

 creatine

1.44

 adrenaline

1.42

Activations Density 0.045%

words related to hormones and neurotransmitters

terms related to hormones and their effects on behavior and health

No Known Activations