INDEX

Explanations

dates from different historical periods

oai_token-act-pair · gpt-3.5-turbo

references to time periods or decades

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

BIL

-0.76

galitarian

-0.73

estic

-0.67

 Generic

-0.66

HP

-0.65

ISA

-0.64

eto

-0.64

BAT

-0.63

 guiActive

-0.63

DA

-0.62

POSITIVE LOGITS

 onwards

1.16

 onward

1.04

 thereafter

0.99

0.97

0.94

0.93

0.88

ixties

0.86

0.81

Activations Density 0.147%

dates from different historical periods

references to time periods or decades

No Comments

No Known Activations