INDEX

Explanations

terms related to rewards or benefits

oai_token-act-pair · gpt-3.5-turbo

references to economic incentives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

room

-0.78

gaard

-0.76

lings

-0.75

erial

-0.75

lain

-0.75

algia

-0.74

mbuds

-0.73

bane

-0.73

uck

-0.72

POSITIVE LOGITS

 incentives

1.07

 incentive

1.07

 incentiv

1.04

 incent

0.97

 rewarded

0.87

Reviewer

0.86

 schemes

0.86

 scheme

0.83

 motivate

0.83

 compulsion

0.81

Activations Density 0.025%

terms related to rewards or benefits

references to economic incentives

No Comments

No Known Activations