INDEX

Explanations

information related to safety procedures or guidelines

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

twitter

-0.75

 Bashar

-0.75

 Maduro

-0.75

 Confederacy

-0.73

 mutants

-0.70

 presided

-0.70

 Murdoch

-0.70

 Plaint

-0.69

iannopoulos

-0.69

 riots

-0.69

POSITIVE LOGITS

 beginner

1.25

 beginners

1.14

Your

1.06

your

1.04

 Tips

1.02

 Helpful

1.02

Learn

1.02

Tips

1.00

 Yourself

0.98

 your

0.97

Activations Density 3.554%

information related to safety procedures or guidelines

No Comments

No Known Activations