INDEX

Explanations

a variety of technical terms related to cyber security and technology, as well as snippets related to recruitment, computer hardware, and public education campaigns

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

senal

-0.56

 alike

-0.53

¥ŀ

-0.53

 Skies

-0.49

idered

-0.48

obo

-0.48

upt

-0.48

 pharmacies

-0.47

«

-0.47

Cooldown

-0.47

POSITIVE LOGITS

1.24

1.23

1.21

1.14

AND

1.10

or

1.04

and

1.02

and

1.02

/$

0.97

/_

0.92

Activations Density 2.583%

a variety of technical terms related to cyber security and technology, as well as snippets related to recruitment, computer hardware, and public education campaigns

No Comments

No Known Activations