INDEX

Explanations

prepositional phrases describing inclusivity or exclusivity

oai_token-act-pair · gpt-3.5-turbo

phrases indicating exclusion or differentiation among groups or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ery

-0.81

dayName

-0.70

matic

-0.65

VERTISEMENT

-0.65

etting

-0.63

igure

-0.63

ike

-0.62

illary

-0.62

rig

-0.62

rogram

-0.60

POSITIVE LOGITS

 ones

0.95

 ours

0.82

those

0.78

 âĶľ

0.76

humans

0.73

 Including

0.71

 those

0.69

 except

0.68

 yours

0.68

 Ones

0.67

Activations Density 0.208%

prepositional phrases describing inclusivity or exclusivity

phrases indicating exclusion or differentiation among groups or categories

No Comments

No Known Activations