INDEX

Explanations

keywords related to incentivizing behaviors or actions

oai_token-act-pair · gpt-3.5-turbo

references to incentives in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ches

-0.71

ister

-0.67

ching

-0.63

isters

-0.63

tou

-0.63

rome

-0.61

yx

-0.60

amber

-0.60

chu

-0.60

istered

-0.60

POSITIVE LOGITS

 incentive

3.68

 incentives

3.51

 incentiv

2.27

 incent

1.79

incent

1.78

 bonuses

1.48

 rewards

1.47

 motivation

1.39

 reward

1.31

 impetus

1.28

Activations Density 0.016%

keywords related to incentivizing behaviors or actions

references to incentives in various contexts

No Comments

No Known Activations