INDEX

Explanations

mentions of hormones

oai_token-act-pair · gpt-3.5-turbo

terms related to hormones and hormone-related discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Ń·

-0.85

lihood

-0.81

Es

-0.75

llah

-0.75

acular

-0.72

ILLE

-0.71

eq

-0.71

zzi

-0.67

alach

-0.66

 Favor

-0.66

POSITIVE LOGITS

 hormones

1.50

 hormone

1.34

 estrogen

1.18

 testosterone

1.16

 hormonal

1.11

 glands

1.09

osterone

1.05

ormonal

1.03

 cortisol

1.00

 secretion

0.99

Activations Density 0.007%

mentions of hormones

terms related to hormones and hormone-related discussions

No Comments

No Known Activations