INDEX

Explanations

sentences or phrases that end with a period

oai_token-act-pair · gpt-3.5-turbo

the presence of punctuation, specifically periods

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

 honored

-0.92

 flavorful

-0.89

 honoring

-0.89

 organizational

-0.88

 enrollment

-0.87

 paycheck

-0.86

 coloring

-0.86

 canceled

-0.85

 colored

-0.83

 labeled

-0.83

POSITIVE LOGITS

 Whilst

1.75

 Firstly

1.42

 Labour

1.28

 Alternatively

1.27

 Ukip

1.25

BBC

1.23

Â£

1.22

 Nato

1.20

 Defence

1.19

 Â£

1.17

Activations Density 0.684%

sentences or phrases that end with a period

the presence of punctuation, specifically periods

No Comments

No Known Activations