INDEX

Explanations

proper nouns related to people or places

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

phis

-0.64

orea

-0.64

 Corpus

-0.63

terson

-0.62

asia

-0.61

alach

-0.61

SUP

-0.61

anooga

-0.61

mercial

-0.61

 Speedway

-0.60

POSITIVE LOGITS

senal

1.31

cliffe

1.14

utherford

0.84

MpServer

0.83

dies

0.81

ledge

0.80

ussia

0.78

aldo

0.77

abbit

0.76

Beer

0.75

Activations Density 1.547%

proper nouns related to people or places

No Comments

No Known Activations