INDEX

Explanations

phrases related to communication and interaction, likely with emotional undertones

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¼ãĥĨ

-0.71

 Downs

-0.69

 recogn

-0.68

 Borough

-0.66

 interf

-0.65

uckland

-0.62

 Thomson

-0.62

 WhatsApp

-0.61

 dispers

-0.61

hots

-0.60

POSITIVE LOGITS

Ļ

1.44

¡

1.18

Ķ

1.16

ĺ

1.12

ł

1.11

«

1.09

ĸ

1.08

ĵ

1.08

Ń

1.08

ľ

1.07

Activations Density 0.254%

phrases related to communication and interaction, likely with emotional undertones

No Comments

No Known Activations