INDEX

Explanations

dates in the format Month Day, Year (e.g., March 26, 2017)

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

keley

-0.71

paio

-0.67

aceae

-0.63

indal

-0.59

 equilibrium

-0.58

cases

-0.57

phia

-0.56

ModLoader

-0.55

 Laboratory

-0.55

 computers

-0.55

POSITIVE LOGITS

advertising

0.78

utm

0.76

à¼

0.72

 Ùħ

0.69

)</

0.68

Loading

0.68

ð

0.67

 VIDEOS

0.67

Ñı

0.67

Reply

0.67

Activations Density 0.509%

dates in the format Month Day, Year (e.g., March 26, 2017)

No Comments

No Known Activations