INDEX

Explanations

environmental and energy-related words

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

 Trib

-0.73

 amen

-0.69

 Raptors

-0.67

***

-0.67

Tud

-0.66

 Schwarz

-0.66

 Amen

-0.65

TRI

-0.65

QU

-0.65

POSITIVE LOGITS

el

1.48

il

1.41

eling

1.34

els

1.31

illian

1.29

iling

1.26

ill

1.22

ils

1.20

iler

1.20

EL

1.17

Activations Density 0.086%

environmental and energy-related words

No Comments

No Known Activations