INDEX

Explanations

IP addresses and network-related 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

loo

-0.67

aida

-0.66

worldly

-0.65

idon

-0.62

sters

-0.62

 Twain

-0.61

yssey

-0.61

 scissors

-0.59

riers

-0.59

repre

-0.58

POSITIVE LOGITS

0.88

percent

0.86

degree

0.86

MPH

0.84

 percentile

0.74

éĹĺ

0.69

deg

0.68

mph

0.67

taboola

0.67

0.66

Activations Density 1.253%

IP addresses and network-related terms

No Comments

No Known Activations