INDEX

Explanations

references to television shows, specifically "Game of Thrones" and related topics

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

arya

-0.75

uve

-0.71

forth

-0.67

pta

-0.65

awei

-0.65

TEXTURE

-0.63

rea

-0.63

 forth

-0.63

 remedy

-0.62

 coli

-0.62

POSITIVE LOGITS

emouth

0.80

Cola

0.71

merce

0.70

TAG

0.70

 guiIcon

0.69

oshenko

0.68

tis

0.67

 nails

0.65

 Trog

0.64

 Mahjong

0.63

Activations Density 2.516%

references to television shows, specifically "Game of Thrones" and related topics

No Comments

No Known Activations