INDEX

Explanations

statements about efforts, actions, or initiatives undertaken to address certain situations or achieve specific goals

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Proud

-0.79

atoon

-0.76

prints

-0.74

ceived

-0.71

 Recorded

-0.71

listed

-0.71

hot

-0.70

 Hate

-0.69

famous

-0.68

laughter

-0.68

POSITIVE LOGITS

 curb

1.41

 avert

1.40

 bolster

1.34

 stabilize

1.33

 stimulate

1.30

 alleviate

1.29

 mitigate

1.29

 counteract

1.26

 reduce

1.26

 tackle

1.24

Activations Density 0.273%

statements about efforts, actions, or initiatives undertaken to address certain situations or achieve specific goals

No Comments

No Known Activations