INDEX

Explanations

phrases related to significant life events or experiences

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

mented

-0.80

essee

-0.73

RECT

-0.72

sonian

-0.72

Ey

-0.71

 Cosponsors

-0.70

CAST

-0.70

unicip

-0.68

REC

-0.65

atchewan

-0.65

POSITIVE LOGITS

 expectancy

1.32

guards

1.08

guard

1.01

blood

0.99

forms

0.98

boat

0.94

 sciences

0.94

mares

0.94

boats

0.91

 everlasting

0.85

Activations Density 0.469%

phrases related to significant life events or experiences

No Comments

No Known Activations