INDEX

Explanations

people of specific origins/locations

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of origin or provenance in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ratulations

-0.86

faced

-0.79

lied

-0.76

important

-0.72

few

-0.72

certain

-0.71

rils

-0.71

blems

-0.70

isec

-0.68

leneck

-0.68

POSITIVE LOGITS

 afar

1.47

 whence

1.22

 thence

1.03

 abroad

1.01

 scratch

0.97

 inside

0.91

 anywhere

0.84

 within

0.83

 elsewhere

0.82

 somewhere

0.79

Activations Density 0.295%

people of specific origins/locations

repeated mentions of origin or provenance in context

No Comments

No Known Activations