INDEX

Explanations

words related to government policy and regulations concerning pensions, healthcare, education, and public services

oai_token-act-pair · gpt-3.5-turbo

terms related to health and social care policies

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

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

 colorful

-0.92

 demeanor

-0.81

colored

-0.81

 feces

-0.79

 Albuquerque

-0.78

 minimized

-0.78

 Hoover

-0.77

 Whitman

-0.77

imize

-0.77

 molded

-0.76

POSITIVE LOGITS

 licences

1.41

 centres

1.34

Scotland

1.32

 programmes

1.31

 organisations

1.27

 licence

1.26

 centre

1.26

 programme

1.25

 Scotland

1.23

MPs

1.21

Activations Density 0.691%

words related to government policy and regulations concerning pensions, healthcare, education, and public services

terms related to health and social care policies

No Comments

No Known Activations