INDEX

Explanations

mentions of the term "white"

oai_token-act-pair · gpt-3.5-turbo

references to the term 'white'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

=-=-=-=-

-0.85

yrinth

-0.82

HCR

-0.81

SIGN

-0.78

cffffcc

-0.77

interstitial

-0.75

ategory

-0.74

itual

-0.74

=-=-

-0.73

Allow

-0.73

POSITIVE LOGITS

 supremacist

1.24

 supremacists

1.08

 nationalist

0.98

 suprem

0.94

 white

0.89

 supremacy

0.87

 elephant

0.86

berry

0.84

 nationalists

0.83

caps

0.82

Activations Density 0.022%

mentions of the term "white"

references to the term 'white'

No Comments

No Known Activations