INDEX

Explanations

words related to legal proceedings, conflict, and regulations

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

ister

-0.65

ä¹ĭ

-0.63

¥ŀ

-0.61

FTWARE

-0.60

ĺħ

-0.60

ĻĤ

-0.59

æł

-0.59

«ĺ

-0.58

 silence

-0.56

ADE

-0.55

POSITIVE LOGITS

roit

1.26

ted

1.19

rix

1.14

rics

1.08

ropolis

1.07

tering

1.03

ters

1.03

ting

1.02

iquette

1.02

ilon

1.02

Activations Density 0.846%

words related to legal proceedings, conflict, and regulations

No Comments

No Known Activations