INDEX

Explanations

source information

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

aeper

-0.94

Ħ¢

-0.87

achine

-0.75

eg

-0.69

esity

-0.68

ecause

-0.66

eer

-0.66

PDATE

-0.64

eers

-0.64

ucket

-0.64

POSITIVE LOGITS

Fed

0.93

books

0.85

 whence

0.85

forge

0.83

book

0.81

alogy

0.78

finding

0.76

Forge

0.72

aneous

0.71

 Sources

0.70

Activations Density 2.077%

source information

No Comments

No Known Activations