INDEX

Explanations

programming-related keywords and phrases

oai_token-act-pair · gpt-3.5-turbo

technical terms and structured data formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 circumcised

-0.83

 disg

-0.76

 cooperating

-0.71

 bush

-0.69

paw

-0.69

.)

-0.67

 nuts

-0.64

 broccoli

-0.64

 acqu

-0.63

SAN

-0.63

POSITIVE LOGITS

":"

1.56

":

1.43

":"","

1.41

":{"

1.40

":[

1.36

Url

1.31

"]=>

1.30

":["

1.27

":[{"

1.26

Type

1.22

Activations Density 0.074%

programming-related keywords and phrases

technical terms and structured data formats

No Comments

No Known Activations