INDEX

Explanations

phrases indicating recognition or acknowledgment, like "credited with" or "credited as."

oai_token-act-pair · gpt-3.5-turbo

references to attributions or acknowledgments of contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

icz

-0.67

cars

-0.62

atos

-0.61

oto

-0.61

ften

-0.61

ife

-0.61

boats

-0.61

ference

-0.61

croft

-0.61

angular

-0.60

POSITIVE LOGITS

olor

0.97

heet

0.84

din

0.80

rious

0.78

llah

0.78

redited

0.75

eworthy

0.72

enza

0.72

VERTISEMENT

0.71

oice

0.71

Activations Density 0.024%

phrases indicating recognition or acknowledgment, like "credited with" or "credited as."

references to attributions or acknowledgments of contributions

No Comments

No Known Activations