INDEX

Explanations

words related to technology or systems that are "based" on something

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

shire

-0.83

unes

-0.75

OUGH

-0.74

olit

-0.71

ubb

-0.71

 Qiao

-0.70

archment

-0.70

wild

-0.70

erved

-0.70

umber

-0.69

POSITIVE LOGITS

 approach

1.02

 economy

1.00

 solutions

0.90

 systems

0.90

 therapies

0.90

 approaches

0.87

 system

0.87

 authentication

0.86

 discrimination

0.83

 policing

0.82

Activations Density 0.058%

words related to technology or systems that are "based" on something

No Comments

No Known Activations