INDEX

Explanations

references to cities, nations, and statistics related to population and displacement

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

 Parables

-0.62

 Defin

-0.59

Klu

-0.56

£ı

-0.54

é¾į

-0.53

 confir

-0.53

é¾įå

-0.53

 tremend

-0.52

 whereas

-0.52

 Dangerous

-0.51

POSITIVE LOGITS

etc

1.11

etc

0.86

0.81

0.79

and

0.74

ect

0.71

ADRA

0.70

,...

0.68

âĢ¦)

0.65

or

0.64

Activations Density 1.101%

references to cities, nations, and statistics related to population and displacement

No Comments

No Known Activations