INDEX

Explanations

phrases related to history, traditions, and origins

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NCT

-0.74

emouth

-0.74

 Spotlight

-0.72

-0.69

PAC

-0.69

ETF

-0.67

Gov

-0.67

rade

-0.66

 Intercept

-0.65

schild

-0.65

POSITIVE LOGITS

 ancient

1.53

 antiquity

1.47

 millennia

1.46

 centuries

1.45

 Ancient

1.38

Ancient

1.37

cients

1.34

 ancestors

1.34

 prehistoric

1.33

 Sanskrit

1.32

Activations Density 0.610%

phrases related to history, traditions, and origins

No Comments

No Known Activations