INDEX

Explanations

references to exclusivity

oai_token-act-pair · gpt-3.5-turbo

terms related to exclusivity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

bridge

-0.73

 Henderson

-0.73

 Geological

-0.70

 Hale

-0.69

 Yang

-0.68

ija

-0.65

imming

-0.64

ulse

-0.62

 Hamilton

-0.62

Reading

-0.61

POSITIVE LOGITS

 exclus

3.93

clus

1.65

 discounts

1.27

exclusive

1.27

 uniqueness

1.24

CLUS

1.16

 confidentiality

1.08

 exemptions

1.03

 warranties

0.99

SOURCE

0.96

Activations Density 0.019%

references to exclusivity

terms related to exclusivity

No Comments

No Known Activations