INDEX

Explanations

keywords related to technical instructions, user guidance, and software management

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

Data Type

torch.float32

Hook Point

blocks.8.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

etheless

-0.87

 compr

-0.78

 nursing

-0.74

 pasture

-0.74

ĻĤ

-0.73

 parks

-0.73

 masked

-0.71

 suburbs

-0.70

 skilled

-0.70

 toget

-0.70

POSITIVE LOGITS

 Manager

1.40

 Agreement

1.28

 Collection

1.27

 Disorder

1.26

 Initiative

1.24

 Builder

1.24

 Definition

1.23

 Generator

1.23

 Mode

1.22

 Suite

1.22

Activations Density 2.166%

keywords related to technical instructions, user guidance, and software management

No Comments

No Known Activations