INDEX

Explanations

references to rankings or positions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating rankings or comparisons in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arre

-0.83

erent

-0.76

lique

-0.73

yden

-0.72

lde

-0.69

plain

-0.66

ses

-0.66

othal

-0.63

iste

-0.62

inge

-0.62

POSITIVE LOGITS

behind

0.93

Ranked

0.89

 surpass

0.89

 Forbes

0.79

 boasting

0.77

 Guinness

0.77

 ranking

0.77

 Ranked

0.73

 Genie

0.73

NYSE

0.73

Activations Density 0.658%

references to rankings or positions

phrases indicating rankings or comparisons in various contexts

No Comments

No Known Activations