INDEX

Explanations

references to media

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

Pis

-0.73

cair

-0.69

ta

-0.69

owsky

-0.67

imov

-0.66

bats

-0.66

sql

-0.65

vasive

-0.64

0000000000000000

-0.64

abouts

-0.63

POSITIVE LOGITS

eval

1.50

 outlets

1.24

 outlet

1.01

 coverage

0.92

 mogul

0.89

mog

0.87

 circus

0.86

 organisations

0.85

 literacy

0.84

 blackout

0.84

Activations Density 0.338%

references to media

No Comments

No Known Activations