INDEX

Explanations

phrases related to problem-solving and analysis

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

-0.80

dayName

-0.75

earchers

-0.75

soever

-0.72

olitical

-0.72

ograms

-0.71

ographies

-0.70

ittees

-0.70

lishes

-0.67

endix

-0.67

POSITIVE LOGITS

 this

1.27

 these

1.03

this

0.90

 THIS

0.86

these

0.83

why

0.80

 polarization

0.80

 inequality

0.78

 causation

0.75

 such

0.72

Activations Density 0.330%

phrases related to problem-solving and analysis

No Comments

No Known Activations