INDEX

Explanations

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 @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rooms

-0.93

lain

-0.83

bane

-0.83

erial

-0.79

room

-0.77

miah

-0.75

mbuds

-0.75

algia

-0.73

ford

-0.72

mac

-0.71

POSITIVE LOGITS

 incentive

1.07

 incentiv

1.05

 incentives

1.04

Reviewer

0.99

 incent

0.93

 rewarded

0.88

 compulsion

0.86

 schemes

0.86

 recipients

0.85

 scheme

0.82

Activations Density 0.023%

references to incentives in various contexts

No Comments

No Known Activations