INDEX

Explanations

technical terms related to computer programming and development processes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Helm

-0.79

 Robot

-0.78

 Haku

-0.77

Mub

-0.76

Sob

-0.74

 Tribal

-0.73

Yad

-0.72

 Axis

-0.72

 wire

-0.71

 Tent

-0.71

POSITIVE LOGITS

Loading

1.30

without

1.29

within

1.23

RAW

1.22

âĹ¼

1.22

together

1.21

Advertisements

1.20

Discussion

1.20

WHERE

1.19

ó

1.18

Activations Density 0.150%

technical terms related to computer programming and development processes

No Comments

No Known Activations