INDEX

Explanations

phrases related to background information or settings

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

chen

-0.80

rone

-0.78

chens

-0.77

boat

-0.72

ateurs

-0.69

ieving

-0.69

dp

-0.69

ikh

-0.67

duct

-0.67

uay

-0.67

POSITIVE LOGITS

spection

0.86

GROUND

0.79

 Background

0.75

 noise

0.74

matter

0.73

 backdrop

0.72

 background

0.70

 backgrounds

0.69

 jumper

0.69

 check

0.67

Activations Density 1.016%

phrases related to background information or settings

No Comments

No Known Activations