INDEX

Explanations

references to people, such as 'people' and 'person'

oai_token-act-pair · gpt-3.5-turbo

references to people involved in events or discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

osterone

-0.85

\/\/

-0.66

 Dragonbound

-0.64

aughs

-0.63

bows

-0.62

esome

-0.62

Kids

-0.62

IFE

-0.62

Rom

-0.61

hibition

-0.59

POSITIVE LOGITS

 involved

1.44

 briefed

1.27

 familiar

1.24

 affiliated

1.24

involved

1.20

 associated

1.14

 knowledgeable

1.11

 connected

1.08

 acquainted

1.04

 interested

1.04

Activations Density 0.271%

references to people, such as 'people' and 'person'

references to people involved in events or discussions

No Comments

No Known Activations