INDEX

Explanations

references to different groups of people, particularly in a cultural or societal context

oai_token-act-pair · gpt-3.5-turbo

references to different ethnic groups and their interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Effective

-0.80

inventoryQuantity

-0.79

nel

-0.77

Accessory

-0.74

thumbnails

-0.72

Delivery

-0.70

ctor

-0.66

 Heller

-0.66

ENTS

-0.64

Repe

-0.64

POSITIVE LOGITS

 peoples

0.98

 civilizations

0.93

hell

0.88

agos

0.86

 nations

0.84

 Languages

0.84

 cultures

0.83

wana

0.83

 inhab

0.79

 countries

0.74

Activations Density 0.081%

references to different groups of people, particularly in a cultural or societal context

references to different ethnic groups and their interactions

No Comments

No Known Activations