INDEX

Explanations

mentions of the word "whiteness" or similar derivatives

oai_token-act-pair · gpt-3.5-turbo

terms related to race, particularly those associated with Whiteness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Population

-0.71

VID

-0.71

 GEAR

-0.69

 Franch

-0.68

ologne

-0.68

Interstitial

-0.66

orsi

-0.65

Reference

-0.65

 SERVICE

-0.65

HAM

-0.65

POSITIVE LOGITS

ewater

1.19

eness

1.13

elist

1.05

 whit

1.02

ipedia

0.90

etooth

0.88

estones

0.87

ening

0.87

estone

0.84

ened

0.84

Activations Density 0.013%

mentions of the word "whiteness" or similar derivatives

terms related to race, particularly those associated with Whiteness

No Comments

No Known Activations