INDEX

Explanations

specific terms related to health, databases, surveys, and research projects

oai_token-act-pair · gpt-3.5-turbo

terms related to health and public safety metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

rising

-0.75

depending

-0.69

 acknow

-0.67

hillary

-0.65

aples

-0.64

comed

-0.62

driving

-0.62

paralle

-0.60

 mechanically

-0.60

romy

-0.60

POSITIVE LOGITS

Ltd

1.10

 Limited

0.93

 Association

0.92

 Development

0.92

 Consortium

0.91

 Facility

0.91

 Authority

0.90

 Fund

0.90

 Simulator

0.87

 Complex

0.87

Activations Density 0.489%

specific terms related to health, databases, surveys, and research projects

terms related to health and public safety metrics

No Comments

No Known Activations