INDEX

Explanations

dates mentioned in text

oai_token-act-pair · gpt-3.5-turbo

numerical dates and references to events occurring on specific days

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

upon

-0.85

ocate

-0.75

enegger

-0.66

Ì¶

-0.66

alach

-0.64

oola

-0.61

orically

-0.61

brace

-0.59

anmar

-0.59

ategory

-0.58

POSITIVE LOGITS

 occasions

1.38

 occasion

1.21

 basis

1.14

ilts

0.97

eve

0.88

imeo

0.87

 shores

0.87

 whim

0.86

 shelf

0.86

 behalf

0.85

Activations Density 0.301%

dates mentioned in text

numerical dates and references to events occurring on specific days

No Comments

No Known Activations