INDEX

Explanations

Twitter handles and hashtags

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

worms

-0.81

apers

-0.74

binding

-0.73

backer

-0.72

 calcul

-0.71

 compens

-0.71

conservancy

-0.70

iculty

-0.68

ordinate

-0.67

ignty

-0.67

POSITIVE LOGITS

————————

1.12

————

0.98

————————————————

0.96

 Ibid

0.95

 âľ

0.85

 âĺ

0.84

 Jonathan

0.83

 Katherine

0.81

 Shaun

0.80

 Jonah

0.79

Activations Density 0.518%

Twitter handles and hashtags

No Comments

No Known Activations