INDEX

Explanations

phrases related to legal and policy matters

oai_token-act-pair · gpt-3.5-turbo

negative prefixes or suffixes related to various topics or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Cooke

-0.85

 Benny

-0.84

 Reyn

-0.83

 Stard

-0.81

 Schumer

-0.80

 Timbers

-0.77

 Dickinson

-0.77

 Kenny

-0.76

 Maher

-0.74

 Twain

-0.74

POSITIVE LOGITS

sounding

1.22

looking

1.16

minded

1.12

advertising

1.09

sense

1.01

intelligence

1.01

marine

0.99

property

0.99

enough

0.98

purpose

0.97

Activations Density 0.083%

phrases related to legal and policy matters

negative prefixes or suffixes related to various topics or issues

No Comments

No Known Activations