INDEX

Explanations

places or locations within a community

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

utes

-0.72

 Lauder

-0.72

 Dragonbound

-0.72

 Leone

-0.71

LV

-0.70

OPE

-0.69

uracy

-0.67

AUT

-0.66

OTOS

-0.66

etimes

-0.64

POSITIVE LOGITS

stay

1.56

tenance

1.27

 culprit

1.09

 tenets

0.97

stream

0.95

 arteries

0.93

 artery

0.93

stone

0.90

 contributor

0.90

iary

0.89

Activations Density 1.106%

places or locations within a community

No Comments

No Known Activations