INDEX

Explanations

words related to wars and conflicts

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

essee

-0.76

 Thumbnails

-0.72

Asset

-0.71

 drawer

-0.67

obook

-0.65

ource

-0.64

 Seller

-0.64

OGR

-0.63

ħĭ

-0.63

erd

-0.62

POSITIVE LOGITS

lords

1.31

rior

1.29

lord

1.28

fare

1.24

riors

1.23

fighting

1.00

fighter

0.99

 waged

0.96

ring

0.96

locks

0.95

Activations Density 0.622%

words related to wars and conflicts

No Comments

No Known Activations