INDEX

Explanations

phrases related to legal and policy-related topics

oai_token-act-pair · gpt-3.5-turbo

terms related to legal and regulatory frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

theless

-0.91

etheless

-0.82

 toget

-0.80

 subscribed

-0.70

ĸļ

-0.69

fortunately

-0.64

 disg

-0.64

 withd

-0.63

anwhile

-0.63

antically

-0.63

POSITIVE LOGITS

 Initiative

1.14

 Disorder

0.99

 Products

0.97

 Development

0.96

 Partners

0.96

 Collection

0.95

 Fund

0.94

 Kits

0.93

 Units

0.93

âĦ¢

0.92

Activations Density 0.391%

phrases related to legal and policy-related topics

terms related to legal and regulatory frameworks

No Comments

No Known Activations