INDEX

Explanations

words related to political figures and positions

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

 Bulg

-0.78

isu

-0.75

afety

-0.70

Cth

-0.69

hedral

-0.68

DW

-0.67

SEA

-0.65

pie

-0.64

xxxxxxxx

-0.63

shapeshifter

-0.62

POSITIVE LOGITS

 nominee

1.73

 frontrunner

1.60

 candidate

1.51

 contender

1.47

 hopeful

1.33

 candidates

1.32

 contenders

1.30

 nominees

1.28

 nomination

1.21

 challenger

1.21

Activations Density 0.056%

words related to political figures and positions

No Comments

No Known Activations