INDEX

Explanations

phrases related to offering or negotiating terms

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

sis

-0.73

FactoryReloaded

-0.71

isol

-0.70

pac

-0.68

alde

-0.64

lean

-0.64

igue

-0.63

cens

-0.63

century

-0.63

cles

-0.63

POSITIVE LOGITS

 condolences

1.03

 refunds

0.91

 discounts

0.91

 suggestions

0.79

 tantal

0.74

 insight

0.73

 advice

0.73

us

0.72

 bribes

0.72

CRIPTION

0.72

Activations Density 0.438%

phrases related to offering or negotiating terms

No Comments

No Known Activations