INDEX

Explanations

terms related to motivation or encouragement, typically in a context where there's a reward or benefit involved

oai_token-act-pair · gpt-3.5-turbo

terms related to incentives and motivations 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

rooms

-0.92

uscript

-0.76

room

-0.75

bane

-0.75

esan

-0.73

rup

-0.72

 Ange

-0.72

gaard

-0.72

abad

-0.70

mbuds

-0.69

POSITIVE LOGITS

 incentive

1.15

 incentives

1.10

 incentiv

1.03

 incent

0.98

 rewarded

0.92

Reviewer

0.92

 schemes

0.89

 scheme

0.87

 compensation

0.87

 compulsion

0.85

Activations Density 0.017%

terms related to motivation or encouragement, typically in a context where there's a reward or benefit involved

terms related to incentives and motivations in various contexts

No Comments

No Known Activations