INDEX

Explanations

words related to negative or harmful actions, such as enslavement, abuse, corruption, and violence

oai_token-act-pair · gpt-3.5-turbo

terms related to social injustices and exploitation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DragonMagazine

-0.97

DonaldTrump

-0.89

 Warriors

-0.70

 Framework

-0.68

 Abyss

-0.67

 Millennium

-0.67

ģĸ

-0.66

OPLE

-0.65

 Paradise

-0.65

Ĥİ

-0.64

POSITIVE LOGITS

icing

0.88

aring

0.85

orting

0.81

iling

0.79

ilit

0.79

ining

0.78

itt

0.78

aking

0.78

eless

0.78

ise

0.78

Activations Density 0.235%

words related to negative or harmful actions, such as enslavement, abuse, corruption, and violence

terms related to social injustices and exploitation

No Comments

No Known Activations