INDEX

Explanations

words related to communication and formalities, such as greetings and expressions of appreciation

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

ories

-0.75

mob

-0.67

 snowball

-0.65

 untreated

-0.65

 debunked

-0.64

 fights

-0.61

 submerged

-0.61

 crumbling

-0.61

 myth

-0.61

fighting

-0.60

POSITIVE LOGITS

 Thank

1.16

 Honour

1.15

Thank

1.14

 thank

1.11

thank

1.03

 honour

1.01

 gracious

1.00

 congratulations

0.99

 congratulate

0.99

Hon

0.99

Activations Density 0.758%

words related to communication and formalities, such as greetings and expressions of appreciation

No Comments

No Known Activations