INDEX

Explanations

mentions of relationships between entities or organizations, particularly parental relationships

oai_token-act-pair · gpt-3.5-turbo

the word "parent" and its associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

atility

-0.86

anwhile

-0.76

 Antar

-0.75

okers

-0.73

 Limbaugh

-0.72

CRIP

-0.69

 Hawks

-0.67

annis

-0.64

schild

-0.63

igslist

-0.63

POSITIVE LOGITS

hetical

1.48

hesis

1.40

hetically

1.16

heses

1.10

 parent

0.94

parents

0.88

 Parent

0.84

hes

0.82

Parents

0.79

Parent

0.79

Activations Density 0.011%

mentions of relationships between entities or organizations, particularly parental relationships

the word "parent" and its associations

No Comments

No Known Activations