INDEX

Explanations

mentions of government regulations or bans

oai_token-act-pair · gpt-3.5-turbo

mentions of regulations, bans, and prohibitions

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

Reviewer

-0.96

cdn

-0.67

LOD

-0.66

Streamer

-0.66

quickShipAvailable

-0.65

want

-0.65

Avg

-0.65

ira

-0.65

MpServer

-0.63

ibaba

-0.63

POSITIVE LOGITS

 lieu

1.17

 schools

1.10

 workplaces

1.09

 classrooms

1.06

 prisons

1.03

 bathrooms

0.99

 restrooms

0.95

 restaurants

0.95

 adulthood

0.92

 favor

0.91

Activations Density 0.240%

mentions of government regulations or bans

mentions of regulations, bans, and prohibitions

No Comments

No Known Activations