INDEX

Explanations

phrases related to politics, news, and organizations

oai_token-act-pair · gpt-3.5-turbo

entities and concepts related to teams and organizational structures

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

 Kraft

-0.70

 Pegasus

-0.63

 Hond

-0.63

osite

-0.62

 mathemat

-0.62

 definite

-0.61

 scaff

-0.60

 Mole

-0.59

 mileage

-0.59

 Kemp

-0.59

POSITIVE LOGITS

âĢ

2.08

*.

1.50

Â»

1.49

âĸł

1.48

Â«

1.48

 âĢ

1.43

ãĢ

1.43

</

1.39

**

1.38

âĢł

1.35

Activations Density 1.074%

phrases related to politics, news, and organizations

entities and concepts related to teams and organizational structures

No Comments

No Known Activations