INDEX

Explanations

terms related to advancements or enhancements

oai_token-act-pair · gpt-3.5-turbo

instances of the word "more" indicating an increase or enhancement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

heid

-0.80

coming

-0.68

DragonMagazine

-0.67

pex

-0.67

etimes

-0.66

 Intervention

-0.65

liest

-0.64

xtap

-0.63

oes

-0.63

DER

-0.63

POSITIVE LOGITS

 than

1.15

 efficient

1.05

 comfortable

0.98

 complicated

0.97

 profitable

0.95

 stringent

0.94

 expensive

0.92

 mature

0.92

 manageable

0.91

 valuable

0.91

Activations Density 0.113%

terms related to advancements or enhancements

instances of the word "more" indicating an increase or enhancement

No Comments

No Known Activations