INDEX

Explanations

phrases related to rights and legislation

oai_token-act-pair · gpt-3.5-turbo

references to human rights

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

aco

-0.67

-+-+

-0.63

 Sark

-0.62

intage

-0.62

ALSE

-0.62

VERSION

-0.60

 steam

-0.60

âĸ¬

-0.59

 threaded

-0.59

 Clover

-0.59

POSITIVE LOGITS

 rights

1.14

 Rights

1.07

rights

1.06

 conferred

0.83

 freedoms

0.83

ileged

0.83

 protections

0.79

 afforded

0.77

 entitle

0.77

hell

0.76

Activations Density 0.024%

phrases related to rights and legislation

references to human rights

No Comments

No Known Activations