INDEX

Explanations

phrases related to collaborative efforts or agreements

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

cens

-0.79

 Wilde

-0.77

hin

-0.77

 Summers

-0.73

Settings

-0.71

landers

-0.70

 atheism

-0.68

 Archangel

-0.67

hunt

-0.66

Unknown

-0.64

POSITIVE LOGITS

 joint

4.06

 Joint

2.49

 joints

2.40

 jointly

1.85

 partnership

1.20

 bilateral

1.16

 junction

1.13

 coordination

1.09

 collaboration

1.00

 sole

1.00

Activations Density 0.003%

phrases related to collaborative efforts or agreements

No Comments

No Known Activations