INDEX

Explanations

scientific or technical terms related to studies or research

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

needed

-0.71

rosso

-0.67

urally

-0.64

oat

-0.59

inctions

-0.59

acerb

-0.57

blems

-0.57

 antidote

-0.57

struction

-0.57

hemy

-0.57

POSITIVE LOGITS

 standpoint

1.63

 onwards

1.37

 vantage

1.26

 perspective

1.17

 onward

1.09

 sources

0.96

 outset

0.87

 viewpoint

0.85

 Shutterstock

0.80

ratch

0.80

Activations Density 0.587%

scientific or technical terms related to studies or research

No Comments

No Known Activations