INDEX

Explanations

phrases related to moral pronouncements or judgments

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'p' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 compe

-0.90

 GOODMAN

-0.76

ãĤ´ãĥ³

-0.70

 Demo

-0.70

 Horizon

-0.69

 Aval

-0.67

 horizont

-0.65

 Exodus

-0.65

MpServer

-0.64

 Shining

-0.63

POSITIVE LOGITS

atern

1.27

ierce

1.27

orters

1.23

uffed

1.22

orter

1.22

ardon

1.19

ascal

1.18

udd

1.13

ussy

1.13

udding

1.13

Activations Density 0.035%

phrases related to moral pronouncements or judgments

occurrences of the letter 'p' in various contexts

No Comments

No Known Activations