INDEX

Explanations

tips or advice shared in a text

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ufact

-0.81

Bom

-0.69

 Affairs

-0.63

yss

-0.62

 sovere

-0.61

ONT

-0.60

ruciating

-0.60

oubted

-0.59

orld

-0.58

 advers

-0.57

POSITIVE LOGITS

tips

1.05

 tips

1.04

tip

1.04

heet

0.98

Tip

0.96

Tips

0.96

 Tips

0.88

tip

0.86

book

0.84

sters

0.82

Activations Density 0.023%

tips or advice shared in a text

No Comments

No Known Activations