INDEX

Explanations

words related to laws and regulations

oai_token-act-pair · gpt-3.5-turbo

references to laws and regulations

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

itate

-0.89

acters

-0.87

itant

-0.84

itÃ©

-0.84

ity

-0.75

 Hots

-0.74

iences

-0.71

velength

-0.70

 Pradesh

-0.68

ãĥ¤

-0.67

POSITIVE LOGITS

book

1.34

making

1.19

books

1.19

breaker

0.99

breaking

0.98

maker

0.97

breakers

0.95

makers

0.90

 breaker

0.86

lessness

0.84

Activations Density 0.033%

words related to laws and regulations

references to laws and regulations

No Comments

No Known Activations