INDEX

Explanations

numerical values and symbols commonly associated with data representation and categorization

oai_token-act-pair · gpt-3.5-turbo

instances of punctuation and formatting markers in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hare

-0.69

']

-0.68

ahu

-0.67

hran

-0.64

ivan

-0.63

 antioxid

-0.60

Afee

-0.60

ipment

-0.59

¬¼

-0.58

auna

-0.56

POSITIVE LOGITS

1.12

0.83

0.81

 whereas

0.79

0.78

 which

0.76

 thereby

0.75

Activations Density 0.247%

numerical values and symbols commonly associated with data representation and categorization

instances of punctuation and formatting markers in the text

No Comments

No Known Activations