INDEX

Explanations

phrases related to data or technical details

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 forwarding

-0.68

ierre

-0.66

iating

-0.64

 lamb

-0.64

aroo

-0.64

 bombshell

-0.63

 sooner

-0.62

onga

-0.62

mitt

-0.60

 stranger

-0.60

POSITIVE LOGITS

 Includes

1.23

 Originally

1.11

 Contains

1.06

 Allows

1.06

 Uses

1.04

 Also

1.03

 Usually

1.00

 Provides

0.99

 These

0.97

 Each

0.97

Activations Density 0.299%

phrases related to data or technical details

No Comments

No Known Activations