INDEX

Explanations

proper nouns or titles

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

references to specific names or titles related to various subjects or entities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

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

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_post

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

cc

-0.43

âĢ¦..

-0.43

âĢ¦.

-0.42

-0.41

 bang

-0.39

/,

-0.38

cou

-0.37

âĢ¦

-0.36

/"

-0.36

—-

-0.36

POSITIVE LOGITS

));

0.67

actionDate

0.66

 Tradable

0.66

 Flavoring

0.57

 pione

0.57

].

0.57

quickShipAvailable

0.56

)))

0.56

 teasp

0.56

)]

0.55

Activations Density 0.272%

proper nouns or titles

references to specific names or titles related to various subjects or entities

No Known Activations