INDEX

Explanations

questioning sentences involving uncertainties or doubts

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

ãģĮ

-0.72

aneers

-0.71

ãģ«

-0.69

brates

-0.65

usters

-0.62

 digs

-0.61

Russ

-0.58

RAFT

-0.58

arez

-0.58

places

-0.58

POSITIVE LOGITS

olated

1.22

olation

1.16

peria

0.96

olate

0.93

abella

0.89

htar

0.87

terness

0.87

berra

0.82

hma

0.78

lington

0.76

Activations Density 0.582%

questioning sentences involving uncertainties or doubts

No Comments

No Known Activations