INDEX

Explanations

references to religious or spiritual experiences

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

 Older

-0.70

onga

-0.69

unique

-0.69

actionDate

-0.69

MK

-0.69

ADVERTISEMENT

-0.67

Times

-0.67

ince

-0.67

iment

-0.67

ANC

-0.67

POSITIVE LOGITS

 then

1.21

 THEN

1.16

 proceeded

1.15

 gave

1.04

 threw

1.03

 began

1.02

 took

0.99

 thereby

0.99

 drove

0.98

 blew

0.97

Activations Density 1.114%

references to religious or spiritual experiences

No Comments

No Known Activations