INDEX

Explanations

references to family relationships, especially parents

oai_token-act-pair · gpt-3.5-turbo

references to parents and their roles or impacts in various situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.77

ocl

-0.68

 Limbaugh

-0.68

atility

-0.65

paio

-0.65

icity

-0.63

 Airl

-0.63

 Baldwin

-0.62

 Antar

-0.62

acity

-0.61

POSITIVE LOGITS

hetical

1.36

hesis

1.26

hetically

0.99

heses

0.98

parents

0.91

hes

0.90

hip

0.83

hood

0.83

hips

0.76

chool

0.73

Activations Density 0.022%

references to family relationships, especially parents

references to parents and their roles or impacts in various situations

No Comments

No Known Activations