INDEX

Explanations

dates and locations mentioned in news articles

oai_token-act-pair · gpt-3.5-turbo

specific dates and times mentioned in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ements

-0.55

ailable

-0.53

 Genie

-0.53

 associations

-0.52

 association

-0.52

anke

-0.51

tion

-0.51

auri

-0.51

rite

-0.50

 testers

-0.50

POSITIVE LOGITS

è£ħ

0.84

 Photographer

0.73

th

0.72

 Shutterstock

0.71

 Courtesy

0.71

bis

0.68

 Photograph

0.67

quin

0.67

UTERS

0.66

 Credit

0.66

Activations Density 0.044%

dates and locations mentioned in news articles

specific dates and times mentioned in the text

No Comments

No Known Activations