INDEX

Explanations

mentions of legal regulations or laws

oai_token-act-pair · gpt-3.5-turbo

references to laws and legal regulations

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

yss

-0.72

ience

-0.69

ortun

-0.65

Naz

-0.65

 Mous

-0.63

arthed

-0.62

atha

-0.62

Dak

-0.62

 Sadd

-0.60

Tur

-0.59

POSITIVE LOGITS

 enforcement

1.30

 governing

1.13

 prohibiting

1.10

enforcement

1.09

 regulating

1.06

 Enforcement

1.05

 enacted

1.00

breakers

0.96

 enforcing

0.94

 restricting

0.93

Activations Density 0.021%

mentions of legal regulations or laws

references to laws and legal regulations

No Comments

No Known Activations