INDEX

Explanations

mentions of statistical information and numerical values

oai_token-act-pair · gpt-3.5-turbo

references to statistical data and numerical information

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itsch

-0.73

 sensibilities

-0.72

 surroundings

-0.71

Stretch

-0.68

 Liberties

-0.66

Dew

-0.63

cheat

-0.63

 arrogance

-0.63

quickShipAvailable

-0.60

 Wrestling

-0.60

POSITIVE LOGITS

 registrations

1.05

 backlog

1.00

 annually

0.93

eligible

0.93

pleted

0.91

 completed

0.89

 births

0.89

 eligible

0.87

 approvals

0.85

 surveyed

0.82

Activations Density 0.586%

mentions of statistical information and numerical values

references to statistical data and numerical information

No Comments

No Known Activations