INDEX

Explanations

concepts related to social issues, specifically segregation and displacement based on race or ethnicity

oai_token-act-pair · gpt-3.5-turbo 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inosaur

-0.69

ube

-0.68

sonian

-0.68

uscript

-0.67

 Drac

-0.65

Cruz

-0.64

leon

-0.63

kos

-0.62

Pad

-0.62

OTAL

-0.61

POSITIVE LOGITS

 segregation

0.96

gregation

0.87

 plantations

0.85

 prejudice

0.83

eering

0.80

heid

0.77

 worsened

0.76

 apartheid

0.75

 neighborhoods

0.75

ocaust

0.74

Activations Density 0.065%

concepts related to social issues, specifically segregation and displacement based on race or ethnicity

No Comments

No Known Activations