INDEX

Explanations

phrases related to actions or events occurring in the past

oai_token-act-pair · gpt-3.5-turbo

references to previous mentions or context in a discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

`.

-1.23

..

-1.23

`,

-1.12

 ..."

-1.01

...

-1.00

"]=>

-0.99

//

-0.97

 ..............

-0.95

 ......

-0.92

POSITIVE LOGITS

—

2.54

)—

2.35

—"

2.34

"—

2.26

—-

1.83

.—

1.78

,—

1.64

——

1.44

Advertisement

1.38

--

1.30

Activations Density 0.667%

phrases related to actions or events occurring in the past

references to previous mentions or context in a discussion

No Comments

No Known Activations