INDEX

Explanations

names of specific entities or figures

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

 beware

-0.77

 patiently

-0.71

 aloud

-0.70

 forcefully

-0.69

 delivered

-0.69

 partake

-0.69

thood

-0.69

 stopping

-0.67

 recite

-0.66

perse

-0.66

POSITIVE LOGITS

oret

1.28

atre

1.24

odor

1.19

 Hague

1.17

resa

1.14

orem

1.09

 Economist

1.06

 Simpsons

1.06

odore

1.03

 Guardian

1.02

Activations Density 0.463%

names of specific entities or figures

No Comments

No Known Activations