INDEX

Explanations

phrases related to political motives or plans

oai_token-act-pair · gpt-3.5-turbo

references to political agendas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

iability

-0.86

avin

-0.76

igi

-0.72

BuyableInstoreAndOnline

-0.72

unte

-0.71

apy

-0.70

ania

-0.70

vation

-0.69

âĵĺ

-0.68

eri

-0.66

POSITIVE LOGITS

 agenda

1.01

eers

0.88

 agendas

0.87

eering

0.85

matic

0.82

 item

0.76

 creep

0.76

geist

0.75

olicy

0.73

posts

0.71

Activations Density 0.043%

phrases related to political motives or plans

references to political agendas

No Comments

No Known Activations