INDEX

Explanations

instances of locations or events being visited

oai_token-act-pair · gpt-3.5-turbo

instances of the word "visited."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

rats

-0.81

corn

-0.75

uscript

-0.73

dry

-0.72

nom

-0.71

assi

-0.71

oil

-0.70

boa

-0.69

absolute

-0.68

smart

-0.67

POSITIVE LOGITS

 visited

1.13

 visits

0.95

 visiting

0.92

ãĥ¼ãĥĨ

0.89

 abroad

0.87

ä»£

0.83

 Disneyland

0.75

 Tours

0.75

 visit

0.74

shire

0.72

Activations Density 0.014%

instances of locations or events being visited

instances of the word "visited."

No Known Activations