INDEX

Explanations

mentions of the color white within social and political contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "white" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

=-=-=-=-

-0.86

yrinth

-0.82

SIGN

-0.74

Completed

-0.73

REC

-0.72

 Inspect

-0.72

ATOR

-0.70

obbies

-0.69

itual

-0.69

rocal

-0.69

POSITIVE LOGITS

 supremacist

1.25

 supremacists

1.12

 suprem

1.01

 white

1.00

lucent

1.00

 nationalist

0.94

white

0.88

 violet

0.86

 supremacy

0.86

 elephant

0.83

Activations Density 0.018%

mentions of the color white within social and political contexts

instances of the word "white" in various contexts

No Comments

No Known Activations