INDEX

Explanations

mentions of legal acts or regulations

oai_token-act-pair · gpt-3.5-turbo

references to legislative acts and laws

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

milo

-0.76

tsky

-0.72

ovych

-0.66

hiba

-0.66

cash

-0.66

holm

-0.65

aturally

-0.64

itness

-0.62

anyl

-0.61

pocket

-0.61

POSITIVE LOGITS

 Amendments

1.02

uary

0.98

ional

0.96

iard

0.83

ors

0.80

Thumbnail

0.80

rine

0.74

ivism

0.72

 enforcement

0.71

Act

0.70

Activations Density 0.022%

mentions of legal acts or regulations

references to legislative acts and laws

No Comments

No Known Activations