INDEX

Explanations

related to specific policies or rules

oai_token-act-pair · gpt-3.5-turbo

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

Ago

-0.80

ingly

-0.77

nces

-0.75

 Stain

-0.73

ITNESS

-0.73

amate

-0.68

ymes

-0.68

DAY

-0.68

 Flavoring

-0.68

ergy

-0.66

POSITIVE LOGITS

holders

1.04

holder

1.02

 prohibiting

1.01

 makers

0.98

 enforcement

0.96

making

0.93

 restricting

0.87

 governing

0.86

 enforced

0.85

 enacted

0.81

Activations Density 0.038%

related to specific policies or rules

No Comments

No Known Activations