INDEX

Explanations

technical terms and numbers related to technology and programming

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

Developer

-0.69

 Religion

-0.64

 Journalism

-0.60

flation

-0.60

abad

-0.59

FontSize

-0.58

Listener

-0.58

 contention

-0.58

hesda

-0.58

soType

-0.57

POSITIVE LOGITS

 batches

0.93

 kinds

0.91

 items

0.83

 dozen

0.81

aneously

0.79

 batch

0.79

 pieces

0.78

 dummy

0.76

 consecut

0.75

izont

0.74

Activations Density 0.519%

technical terms and numbers related to technology and programming

No Comments

No Known Activations