INDEX

Explanations

references to legal or ethical consent in social contexts

oai_token-act-pair · gpt-3.5-turbo

terms and concepts related to consent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Tycoon

-0.82

nas

-0.70

mania

-0.70

 Bulgar

-0.67

tera

-0.66

tin

-0.66

ched

-0.63

 Lantern

-0.61

gaard

-0.61

 Canaver

-0.60

POSITIVE LOGITS

 decree

1.06

 consent

1.02

ible

0.99

ing

0.93

ibility

0.88

 decre

0.87

 Consent

0.87

ivation

0.85

urable

0.83

ignt

0.78

Activations Density 0.030%

references to legal or ethical consent in social contexts

terms and concepts related to consent

No Comments

No Known Activations