INDEX

Explanations

decisions or the act of making decisions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

bour

-0.81

Mania

-0.71

 Niet

-0.70

hood

-0.63

Fram

-0.62

Demon

-0.58

 Ples

-0.57

 alluded

-0.56

hens

-0.56

agher

-0.55

POSITIVE LOGITS

 decisions

1.15

 sure

1.13

 mistakes

1.08

 adjustments

1.03

 assumptions

1.01

 judgments

0.99

 excuses

0.98

hift

0.94

 choices

0.92

 strides

0.91

Activations Density 0.134%

decisions or the act of making decisions

No Comments

No Known Activations