INDEX

Explanations

phrases related to attention or emphasis on a particular subject or object

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

named

-0.73

OUGH

-0.73

ania

-0.73

mia

-0.69

ston

-0.66

mx

-0.62

BIT

-0.61

Haunted

-0.61

adding

-0.61

asca

-0.61

POSITIVE LOGITS

 focus

1.02

rite

0.95

 focused

0.93

 focuses

0.89

foc

0.89

 squarely

0.85

 focusing

0.85

focus

0.83

peed

0.83

phasis

0.82

Activations Density 0.717%

phrases related to attention or emphasis on a particular subject or object

No Comments

No Known Activations