INDEX

Explanations

phrases related to questions or queries

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

sson

-0.71

 Fract

-0.69

Seg

-0.64

Vaj

-0.60

ger

-0.60

 Ludwig

-0.60

 Franc

-0.57

 Sans

-0.57

cles

-0.56

arte

-0.56

POSITIVE LOGITS

eties

0.98

·

0.97

ole

0.95

olly

0.93

¸

0.91

OA

0.90

bour

0.88

terness

0.87

erver

0.87

ework

0.86

Activations Density 0.103%

phrases related to questions or queries

No Comments

No Known Activations