INDEX

Explanations

dates in various formats

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

 VIDEOS

-0.77

amines

-0.70

bom

-0.66

 diaper

-0.66

 inherit

-0.63

cro

-0.62

 juggling

-0.61

opic

-0.61

MET

-0.59

ioch

-0.59

POSITIVE LOGITS

1.35

1.30

1.27

1.26

1.25

1.23

1.21

1.20

1.14

Activations Density 0.305%

dates in various formats

No Comments

No Known Activations