INDEX

Explanations

words related to exceptions, exclusions, or special permissions

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to exemptions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ãĥ¥

-0.73

aces

-0.69

plays

-0.68

 Roose

-0.67

 Hurricanes

-0.64

KR

-0.63

 Bras

-0.62

aptic

-0.62

 Xiang

-0.62

 Zeit

-0.61

POSITIVE LOGITS

 exempt

1.15

 exemptions

1.07

 exemption

0.99

 exempted

0.99

exempt

0.97

 immunity

0.92

Reviewer

0.88

emption

0.83

untarily

0.82

icut

0.78

Activations Density 0.020%

words related to exceptions, exclusions, or special permissions

terms and phrases related to exemptions in various contexts

No Comments

No Known Activations