INDEX

Explanations

phrases related to rights, laws, and beliefs

oai_token-act-pair · gpt-3.5-turbo

discussions on legal rights and personal freedoms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

luster

-0.94

 bullish

-0.89

 upbeat

-0.79

 pione

-0.74

 pessimistic

-0.73

 teasp

-0.71

iscovered

-0.71

iosyn

-0.70

senal

-0.69

arbon

-0.69

POSITIVE LOGITS

 legality

1.07

 prohibiting

1.06

 violates

1.06

 unlaw

1.02

 prohibit

1.02

 prohibitions

1.02

 exemptions

1.00

 exemption

0.99

 lawful

0.99

 prohibits

0.98

Activations Density 0.712%

phrases related to rights, laws, and beliefs

discussions on legal rights and personal freedoms

No Comments

No Known Activations