INDEX

Explanations

mentions of positions or roles as a "Deputy."

oai_token-act-pair · gpt-3.5-turbo

references to deputy positions in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ĸļ

-0.91

stakes

-0.90

 Gutenberg

-0.81

oven

-0.80

hetti

-0.78

ebook

-0.78

eka

-0.76

OPA

-0.76

cott

-0.73

azed

-0.72

POSITIVE LOGITS

uty

1.05

 deputy

1.00

 assistant

0.85

 Deputy

0.83

 chief

0.81

 lieutenant

0.79

 Assistant

0.78

 adjunct

0.77

 clerks

0.76

 director

0.75

Activations Density 0.014%

mentions of positions or roles as a "Deputy."

references to deputy positions in various contexts

No Comments

No Known Activations