INDEX

Explanations

words related to perfection or ideal situations

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

Downloadha

-0.89

SEE

-0.84

iers

-0.76

ker

-0.75

cohol

-0.72

NetMessage

-0.71

ktop

-0.71

cipl

-0.68

ulative

-0.68

ickr

-0.67

POSITIVE LOGITS

ion

0.89

 blend

0.88

ions

0.81

 encaps

0.79

 timing

0.76

 suited

0.76

 harmony

0.75

 symmetry

0.74

imum

0.73

 forwarding

0.73

Activations Density 0.661%

words related to perfection or ideal situations

No Comments

No Known Activations