INDEX

Explanations

specific numeric values and associated measurements or quantities

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

specific numbers and measurements mentioned in the text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Neuroscience

-0.73

 PubMed

-0.72

 Shutterstock

-0.71

atically

-0.70

 Machina

-0.64

ifully

-0.63

 Authors

-0.61

mining

-0.59

 Gupta

-0.58

 Greenwald

-0.58

POSITIVE LOGITS

%-

0.96

ÃĹ

0.96

th

0.91

 gallon

0.87

Hz

0.85

mm

0.84

 watt

0.83

âĢ³

0.81

 inch

0.81

kHz

0.79

Activations Density 0.240%

specific numeric values and associated measurements or quantities

specific numbers and measurements mentioned in the text

No Comments

No Known Activations