INDEX

Explanations

proper nouns related to relationships or interactions between individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of characters and their interactions

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

ontent

-0.72

corruption

-0.72

catentry

-0.71

 Hilbert

-0.70

Effective

-0.68

actionDate

-0.66

Ct

-0.66

 Berman

-0.65

"[

-0.64

SPONSORED

-0.64

POSITIVE LOGITS

 nodded

1.48

 smiled

1.47

 glanced

1.44

 paused

1.42

 grinned

1.39

 stared

1.35

 hesitated

1.34

 sighed

1.27

 gazed

1.25

 chuckled

1.24

Activations Density 0.181%

proper nouns related to relationships or interactions between individuals

mentions of characters and their interactions

No Comments

No Known Activations