INDEX

Explanations

mentions of discoveries or practices

oai_token-act-pair · gpt-3.5-turbo

terms related to agreements and negotiations

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

 Eternity

-0.66

Dialogue

-0.62

BuyableInstoreAndOnline

-0.62

Ow

-0.61

Save

-0.60

 Contributions

-0.59

ļéĨĴ

-0.58

 Gork

-0.58

Vis

-0.58

 Enough

-0.57

POSITIVE LOGITS

 prevalent

1.28

 pioneered

1.05

 commonplace

1.04

 practiced

1.01

 widespread

1.00

 coined

0.96

 commonly

0.95

common

0.95

 pervasive

0.94

 ubiquitous

0.92

Activations Density 0.685%

mentions of discoveries or practices

terms related to agreements and negotiations

No Comments

No Known Activations